© 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. 44242
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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
    ’，
    -1.93
    ieteur
    -1.47
    ForResult
    -1.47
    atuur
    -1.45
     Any
    -1.38
    ято
    -1.37
    ”，
    -1.37
     theyre
    -1.34
     for
    -1.30
    ѝ
    -1.29
    POSITIVE LOGITS
     that
    1.72
     possibility
    1.62
    "
    1.56
     Möglichkeit
    1.51
     besi
    1.48
    據
    1.48
    sistence
    1.41
    would
    1.38
     druge
    1.38
    身后的
    1.37
    Activations Density 0.009%

    No Known Activations