© 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. 129383
    Prev
    Next
    INDEX
    Explanations

    file paths and codes

    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
     for
    -2.06
     any
    -1.98
     some
    -1.83
     more
    -1.83
     even
    -1.80
     those
    -1.79
     many
    -1.76
     by
    -1.76
     if
    -1.72
     Even
    -1.70
    POSITIVE LOGITS
     trám
    1.91
     insanely
    1.70
     unending
    1.67
     soooo
    1.63
     horrifying
    1.63
     unbelievably
    1.63
     rác
    1.59
     breathtaking
    1.58
     AMAZING
    1.56
     astonishing
    1.55
    Activations Density 0.003%

    No Known Activations