© 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. 32524
    Prev
    Next
    INDEX
    Explanations

    References

    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
     transformación
    -0.82
    GEE
    -0.79
     instead
    -0.74
    💇
    -0.73
     colocación
    -0.72
    filelist
    -0.72
    bingo
    -0.71
    amat
    -0.71
    urg
    -0.71
    推荐阅读
    -0.71
    POSITIVE LOGITS
    ļas
    0.91
     одна
    0.82
     AX
    0.81
    ۚ
    0.79
    hamento
    0.77
     Internal
    0.76
    initas
    0.75
    ItemGroup
    0.74
    assion
    0.73
    ituksen
    0.73
    Activations Density 0.005%

    No Known Activations