© 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. 78627
    Prev
    Next
    INDEX
    Explanations

    XYZ coordinates

    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
     mostrare
    -0.79
    ͮ
    -0.77
     abrir
    -0.75
     Yvette
    -0.75
    YAxis
    -0.74
     Lampe
    -0.73
     என
    -0.73
    getY
    -0.73
     квітня
    -0.73
     Y
    -0.72
    POSITIVE LOGITS
     Z
    0.98
    Z
    0.94
    getZ
    0.94
     z
    0.89
    IZ
    0.86
     Zumba
    0.84
     RZ
    0.82
     conic
    0.79
     veh
    0.79
     IZ
    0.78
    Activations Density 0.008%

    No Known Activations