© 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. 22-GEMMASCOPE-RES-131K
    7. 65083
    Prev
    Next
    INDEX
    Explanations

    patterns of 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_22/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
     Diſ
    -1.17
     précédente
    -1.12
    ̍t
    -1.09
    sieu
    -1.08
     numerosi
    -1.06
    hebt
    -1.04
    tuj
    -1.03
     intitulée
    -1.02
    ſten
    -1.02
     المعلومات
    -1.01
    POSITIVE LOGITS
     saurait
    1.01
     revelou
    0.95
     or
    0.94
    om
    0.93
     While
    0.92
     afirmou
    0.92
    起始
    0.91
     mostrou
    0.91
     in
    0.89
    man
    0.89
    Activations Density 0.550%

    No Known Activations