© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41182
    Prev
    Next
    INDEX
    Explanations

    computer instructions

    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_10/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
    她的
    -2.14
     эту
    -1.89
     ihrer
    -1.87
     péché
    -1.84
    or
    -1.82
    but
    -1.78
     rendus
    -1.77
     pièce
    -1.76
    =\""
    -1.76
     ditt
    -1.75
    POSITIVE LOGITS
     After
    2.03
    .
    1.98
    ଽ
    1.95
    🅣
    1.95
    哢
    1.91
     После
    1.88
    翃
    1.88
     беже
    1.85
     Therefore
    1.84
     Universitaria
    1.84
    Activations Density 0.007%

    No Known Activations