© 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. 5402
    Prev
    Next
    INDEX
    Explanations

    IAM permissions or RAM requirements

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

    This neuron fires on Unix file-permission mode specifiers (e.g. the “g+w”/“g+rw” pieces in chmod commands).

    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
    勅
    0.63
    тони
    0.61
    उदा
    0.61
     sogen
    0.61
    tickers
    0.59
    醇
    0.59
    MsgCallBack
    0.59
    outputText
    0.58
    methylation
    0.58
    ATPase
    0.57
    POSITIVE LOGITS
     місце
    0.73
     badan
    0.71
     якщо
    0.68
     giám
    0.68
     проверя
    0.68
     dacă
    0.65
     đừng
    0.65
     unremarkable
    0.65
     ド
    0.64
     aura
    0.63
    Activations Density 0.117%

    No Known Activations