© 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. 72420
    Prev
    Next
    INDEX
    Explanations

    fieldbus, Scanner, sequential treatments, rotating, double Array, post prandial, absorbing green glass

    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
     of
    -1.27
    no
    -1.01
    both
    -0.99
    end
    -0.95
    best
    -0.92
     teat
    -0.92
    their
    -0.91
     クリップ
    -0.89
    now
    -0.88
    ru
    -0.88
    POSITIVE LOGITS
    　　「
    0.98
     」
    0.96
     kré
    0.95
    Batis
    0.94
     TWO
    0.92
     ``
    0.92
     ialah
    0.91
     kompakt
    0.91
    тилась
    0.91
    이크
    0.90
    Activations Density 0.076%

    No Known Activations