© 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. 93311
    Prev
    Next
    INDEX
    Explanations

    may not use

    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
     kän
    -0.84
    ņ
    -0.81
     required
    -0.81
     through
    -0.81
     wiedzieć
    -0.79
     during
    -0.79
     倍
    -0.79
    载
    -0.78
    Often
    -0.76
     skriv
    -0.76
    POSITIVE LOGITS
     ments
    1.02
    atia
    0.96
     PRED
    0.91
    lig
    0.90
     DIST
    0.87
     HOR
    0.87
     DISCIP
    0.86
    hor
    0.86
    nade
    0.85
     GUIDE
    0.85
    Activations Density 0.000%

    No Known Activations