© 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. 41613
    Prev
    Next
    INDEX
    Explanations

    ways to shape or qualify

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

    selection import

    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
     forl
    0.48
    慳
    0.45
    岨
    0.45
     صارف
    0.44
    ئے۔
    0.44
     ابھی
    0.43
     ندار
    0.43
    善良
    0.43
    嫦
    0.43
    無理
    0.43
    POSITIVE LOGITS
    electrode
    0.50
     electrode
    0.44
    ddot
    0.43
     contoured
    0.43
     Wax
    0.43
     electrodes
    0.43
    ppt
    0.42
     inch
    0.42
    enriched
    0.42
     reshape
    0.41
    Activations Density 0.000%

    No Known Activations