© 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. 48654
    Prev
    Next
    INDEX
    Explanations

    license files

    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
    llvm
    -0.76
    COMMUNITY
    -0.70
     Hurts
    -0.70
    BlockPos
    -0.70
    çal
    -0.69
     biological
    -0.69
     Keller
    -0.68
    cabul
    -0.68
     vacunación
    -0.67
     ролях
    -0.67
    POSITIVE LOGITS
     Logo
    0.76
    Архівовано
    0.72
    quot
    0.70
    witt
    0.69
    йте
    0.69
    setAll
    0.68
     Kabir
    0.67
     Nee
    0.67
    onent
    0.66
     counterfeit
    0.66
    Activations Density 0.031%

    No Known Activations