© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    file named, website, states, words

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

    The neuron strongly activates on unusually rare or low‐frequency tokens, i.e. words that seldom appear in typical text.

    oai_token-act-pair · o4-miniTriggered 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
    altezza
    0.88
    branco
    0.79
    oxygène
    0.73
    chip
    0.73
    ंबल
    0.73
    asem
    0.73
     supérieur
    0.73
    ]][
    0.71
    ázat
    0.71
    empi
    0.71
    POSITIVE LOGITS
     dances
    0.80
     remittance
    0.77
     Nurs
    0.71
     ATS
    0.70
     entertainers
    0.70
     இருப்பது
    0.70
    ダンス
    0.69
     harming
    0.69
     graces
    0.69
     dancing
    0.68
    Activations Density 0.001%

    No Known Activations