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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15756
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations and programming

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

    The neuron fires on code method/function declarations, i.e. the signature line with return type, method name, and its parenthesized parameter list.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -1.14
    itself
    -0.90
    这样
    -0.86
     natureza
    -0.79
    UIL
    -0.77
    ienki
    -0.77
    フィット
    -0.77
     maisha
    -0.77
     likewise
    -0.76
    ママ
    -0.76
    POSITIVE LOGITS
     with
    0.90
     zwią
    0.81
     hubo
    0.81
    Ǵ
    0.79
    ременно
    0.79
     initWith
    0.79
    ッシャー
    0.78
    閹
    0.76
    ervlak
    0.75
    するか
    0.74
    Activations Density 0.091%

    No Known Activations