© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3432
    Prev
    Next
    INDEX
    Explanations

    Gardening, project methods, company examples, sports figures, historical figures, space missions, movie characters, outdoor gear

    np_acts-logits-general · gemini-2.5-flash-lite

    parenthetical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    0.47
     پ
    0.44
    缑
    0.44
     visualizations
    0.43
     spline
    0.43
     cyborg
    0.43
     مە
    0.42
     straps
    0.40
     bronch
    0.40
     monadic
    0.40
    POSITIVE LOGITS
    <h3>
    0.56
    However
    0.49
    While
    0.46
    <h2>
    0.45
    ud
    0.45
    As
    0.45
    Pre
    0.44
    The
    0.44
    According
    0.43
    Since
    0.43
    Activations Density 0.073%

    No Known Activations