© 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. 43814
    Prev
    Next
    INDEX
    Explanations

    programming annotations

    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
     in
    -1.54
     considerados
    -1.46
     pesados
    -1.36
     nutrientes
    -1.34
     If
    -1.34
     from
    -1.32
     fantástica
    -1.31
     only
    -1.30
     masiva
    -1.30
     черная
    -1.27
    POSITIVE LOGITS
    6
    1.66
    Where
    1.63
     vélos
    1.50
    '
    1.47
    .
    1.45
     WEEKS
    1.41
     كنت
    1.41
     FIFTH
    1.40
     -"
    1.39
    ycznego
    1.39
    Activations Density 0.022%

    No Known Activations