© 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. 10-GEMMASCOPE-RES-131K
    7. 85511
    Prev
    Next
    INDEX
    Explanations

    Stack Overflow programming help

    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
     The
    -1.89
     That
    -1.84
     From
    -1.72
     By
    -1.68
     による
    -1.66
     for
    -1.63
     FROM
    -1.63
     从
    -1.62
     如果
    -1.62
     Если
    -1.59
    POSITIVE LOGITS
    the
    2.38
    今月
    2.08
    ”
    2.08
    Ꭳ
    1.95
    鰨
    1.87
     твоя
    1.85
    紧接着
    1.84
    ."
    1.81
    Ꮚ
    1.78
     samme
    1.71
    Activations Density 0.008%

    No Known Activations