© 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. 78164
    Prev
    Next
    INDEX
    Explanations

    socket.io client connection

    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
    herd
    -0.91
    匱
    -0.84
     drawback
    -0.78
     Jedes
    -0.78
    وش
    -0.76
    amını
    -0.76
    MLP
    -0.73
    冂
    -0.73
    MCM
    -0.72
    phylactic
    -0.71
    POSITIVE LOGITS
     inférieure
    0.82
     Kui
    0.81
    一起去
    0.79
    نحوه
    0.77
     انف
    0.77
     卵
    0.77
     petitioners
    0.75
     प्रकार
    0.75
     ido
    0.74
     fisherman
    0.73
    Activations Density 0.016%

    No Known Activations