© 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. 58201
    Prev
    Next
    INDEX
    Explanations

    SOFTWARE NOTICE AND LICENSE

    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
     PROPER
    -0.83
    upported
    -0.72
    ühle
    -0.71
     figure
    -0.70
    Figures
    -0.70
    Vidéo
    -0.70
     הול
    -0.70
    Sites
    -0.69
    Altro
    -0.68
    Forums
    -0.66
    POSITIVE LOGITS
     township
    0.79
    ZZ
    0.71
     Lipschitz
    0.70
     sierpnia
    0.69
     Caro
    0.69
    💥
    0.67
    Ë
    0.66
    бут
    0.65
    ()`
    0.65
    usk
    0.65
    Activations Density 0.063%

    No Known Activations