© 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. 93266
    Prev
    Next
    INDEX
    Explanations

    questions about location and input

    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
     turn
    -0.87
    готови
    -0.82
    先は
    -0.76
    žių
    -0.75
    Mgmt
    -0.74
    azon
    -0.71
     carreteras
    -0.69
    ってみる
    -0.69
     教室
    -0.68
     prote
    -0.67
    POSITIVE LOGITS
    avoid
    1.05
     avoids
    0.90
    Avoid
    0.88
     avoid
    0.88
     Avoid
    0.87
    输入
    0.84
    輸入
    0.81
    Calculate
    0.80
     preferences
    0.75
     input
    0.74
    Activations Density 0.029%

    No Known Activations