© 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. 26765
    Prev
    Next
    INDEX
    Explanations

    module paths and library names

    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
    izzling
    -0.96
     می‌گو
    -0.95
     huo
    -0.94
    RAINE
    -0.92
    riy
    -0.92
     și
    -0.91
     which
    -0.91
     their
    -0.89
    $-.
    -0.88
    ).—
    -0.88
    POSITIVE LOGITS
    While
    1.23
     стандарт
    1.09
     gewünschten
    1.02
    Although
    1.00
     Aseg
    0.98
    There
    0.97
    Since
    0.96
     Araújo
    0.96
    Among
    0.95
    標準
    0.95
    Activations Density 0.073%

    No Known Activations