© 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. 22-GEMMASCOPE-RES-131K
    7. 15324
    Prev
    Next
    INDEX
    Explanations

    punctuations followed by code constructs

    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_22/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
    ねえ
    -0.99
     vín
    -0.95
    לל
    -0.94
    ingway
    -0.93
     anecd
    -0.91
    lho
    -0.91
     pirata
    -0.90
     verzi
    -0.90
     verla
    -0.90
     descuento
    -0.90
    POSITIVE LOGITS
     that
    1.09
     което
    0.88
     president
    0.86
     (
    0.80
     common
    0.80
     all
    0.79
     comes
    0.79
     fundamental
    0.79
     her
    0.77
     --
    0.76
    Activations Density 0.008%

    No Known Activations