© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14115
    Prev
    Next
    INDEX
    Explanations

    lists containing numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron spikes on unusually rare or low‐frequency tokens (i.e. words or symbols that seldom occur in normal text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers embedded within formal or technical text, particularly in contexts involving dates, measurements, legal references, or product specifications.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    short prepositional function words indicating relations (e.g., spatial or abstract links between phrases).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сти
    0.82
     рода
    0.78
    нное
    0.76
    ្វ
    0.70
     стало
    0.70
     וב
    0.70
    йки
    0.70
    Mutability
    0.70
     fruition
    0.68
    ш
    0.68
    POSITIVE LOGITS
     Arturo
    0.88
    荖
    0.87
     IGBT
    0.87
     effettuare
    0.84
    vive
    0.80
     Muitos
    0.79
     Poker
    0.78
     magar
    0.77
     Anand
    0.77
    zki
    0.77
    Activations Density 0.000%

    No Known Activations