© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64649
    Prev
    Next
    INDEX
    Explanations

    hag- words

    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
     Brides
    -0.79
    role
    -0.75
    vás
    -0.74
     Picchu
    -0.71
    vég
    -0.71
     adulter
    -0.69
    協助
    -0.69
     divider
    -0.69
     اجرا
    -0.69
    kadın
    -0.68
    POSITIVE LOGITS
     artifact
    0.74
    общение
    0.70
    intptr
    0.69
    🧛
    0.69
    Supplementary
    0.69
    有什么
    0.69
     pesos
    0.68
    seth
    0.68
    arty
    0.68
    tih
    0.68
    Activations Density 0.022%

    No Known Activations