© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10879
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on infrequent content words (i.e. rarer tokens) regardless of their part of speech.

    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
    iz
    0.85
    lessness
    0.84
    izes
    0.82
     contended
    0.79
    kana
    0.78
    َف
    0.78
    versa
    0.77
     ($\
    0.77
     supremum
    0.77
    fool
    0.76
    POSITIVE LOGITS
     полови
    0.77
    ר
    0.77
     новый
    0.75
     получение
    0.74
    sqlUpdate
    0.72
    いく
    0.71
    서
    0.70
    сы
    0.68
     ruedas
    0.68
    ০০
    0.67
    Activations Density 0.000%

    No Known Activations