© 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. 34-GEMMASCOPE-RES-131K
    7. 92865
    Prev
    Next
    INDEX
    Explanations

    express or implied

    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
    無理
    -0.82
    telefon
    -0.82
     indicando
    -0.81
    стина
    -0.79
     unfair
    -0.79
    UserGroup
    -0.77
     որ
    -0.77
     agak
    -0.76
     balanceOf
    -0.75
     Botan
    -0.75
    POSITIVE LOGITS
    ണ്
    0.79
    Üdv
    0.76
    ",
    0.73
     wł
    0.72
     Ever
    0.71
    ,@
    0.71
    Edit
    0.70
    ヌー
    0.70
     @
    0.69
     ov
    0.69
    Activations Density 0.002%

    No Known Activations