© 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. 117278
    Prev
    Next
    INDEX
    Explanations

    sitting in or at

    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
     niente
    -0.79
    讶
    -0.77
     této
    -0.76
     seigneur
    -0.76
    wiada
    -0.75
     Tisch
    -0.75
     jesús
    -0.73
    稍
    -0.72
    भग
    -0.72
     Gesang
    -0.72
    POSITIVE LOGITS
     there
    1.82
     in
    1.04
     waiting
    0.97
     on
    0.89
     там
    0.88
     their
    0.86
     هناك
    0.85
    mær
    0.85
    There
    0.84
    ի
    0.83
    Activations Density 0.011%

    No Known Activations