© 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. 34-GEMMASCOPE-RES-131K
    7. 92861
    Prev
    Next
    INDEX
    Explanations

    code punctuation and markers

    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_34/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
    баты
    -0.71
    менения
    -0.69
     os
    -0.68
    dea
    -0.68
     cartoon
    -0.68
     род
    -0.68
     wait
    -0.67
     Small
    -0.66
     nicht
    -0.65
     przypad
    -0.65
    POSITIVE LOGITS
     Typo
    0.75
    jac
    0.75
    ㎖
    0.69
    )^
    0.69
     quads
    0.68
     Subsection
    0.67
     steppe
    0.66
     jungkook
    0.65
     kefir
    0.65
     naph
    0.65
    Activations Density 0.054%

    No Known Activations