© 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. 26842
    Prev
    Next
    INDEX
    Explanations

    numbers or elements in sequences

    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
    .*;
    -0.96
    LLLL
    -0.96
    istische
    -0.96
     eſt
    -0.95
    潜水
    -0.93
    mannschaft
    -0.91
    МЕН
    -0.91
    uszka
    -0.91
     ............
    -0.90
    фы
    -0.89
    POSITIVE LOGITS
     these
    1.28
     their
    1.12
     `
    1.05
    —
    1.02
     at
    0.98
     in
    0.96
    หน้าน
    0.93
     this
    0.93
    .”
    0.91
     two
    0.90
    Activations Density 0.019%

    No Known Activations