© 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. 57858
    Prev
    Next
    INDEX
    Explanations

    tooltip or tips

    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
    宽
    -0.77
     Brick
    -0.76
     Bearer
    -0.74
    ᵣ
    -0.73
     brick
    -0.71
     מתח
    -0.71
    traction
    -0.71
     brazil
    -0.70
     Hybrid
    -0.69
    тай
    -0.68
    POSITIVE LOGITS
     tooltip
    2.00
     Tooltip
    1.76
     tips
    1.73
     tip
    1.72
    tooltip
    1.72
    Tooltip
    1.56
    tip
    1.52
    Tip
    1.51
    tips
    1.49
    TIP
    1.41
    Activations Density 0.030%

    No Known Activations