© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11783
    Prev
    Next
    INDEX
    Explanations

    code file headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     QtWidgets
    -0.82
    %%%%%%
    -0.82
     København
    -0.82
    bilirsiniz
    -0.81
    fand
    -0.81
    чва
    -0.81
    dryer
    -0.80
    providedIn
    -0.80
    hx
    -0.80
    =_
    -0.79
    POSITIVE LOGITS
    let
    1.06
     let
    0.93
     sour
    0.80
     biographer
    0.75
     sostener
    0.75
     Weaver
    0.71
     pensamientos
    0.71
     ライ
    0.71
     達
    0.71
    凄く
    0.71
    Activations Density 0.010%

    No Known Activations