© 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. 77926
    Prev
    Next
    INDEX
    Explanations

    images and documentation

    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
     there
    -1.01
    QColor
    -0.95
     google
    -0.91
    Referees
    -0.88
     those
    -0.88
     low
    -0.86
    كد
    -0.85
     markedly
    -0.82
     my
    -0.82
     们
    -0.81
    POSITIVE LOGITS
    เกี่ยวกับ
    1.10
    关于
    1.09
    關於
    1.00
     consentement
    0.99
    亹
    0.97
     mobilier
    0.90
     notizie
    0.89
    forcement
    0.87
     imagery
    0.86
    Weiter
    0.85
    Activations Density 0.001%

    No Known Activations