© 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. 63853
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and code blocks

    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
    stanley
    -1.02
    鏟
    -0.99
    Trichloroethane
    -0.94
    olesale
    -0.93
     aktiviteter
    -0.93
     činnosti
    -0.92
     pourtant
    -0.92
    Alexandre
    -0.91
    icei
    -0.91
    borsa
    -0.90
    POSITIVE LOGITS
     even
    1.09
     also
    1.04
    Then
    1.00
    for
    0.97
    These
    0.95
    Even
    0.93
     regarded
    0.92
     then
    0.91
    They
    0.89
     etiam
    0.88
    Activations Density 0.012%

    No Known Activations