© 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. 15826
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
    u
    -1.91
     and
    -1.71
     which
    -1.66
     or
    -1.59
     cautious
    -1.55
    er
    -1.54
     various
    -1.52
    ir
    -1.52
    e
    -1.52
     innumerable
    -1.51
    POSITIVE LOGITS
     that
    2.69
    wiſe
    2.03
    盌
    1.94
     it
    1.88
    がありません
    1.77
     penyanyi
    1.69
    塒
    1.67
     there
    1.66
     Informações
    1.63
    <<<<<<<<<<<<
    1.61
    Activations Density 0.027%

    No Known Activations