© 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. 115761
    Prev
    Next
    INDEX
    Explanations

    decide among

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

    zip, plastics, visa

    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
    0
    0.45
    He
    0.44
     associative
    0.42
    贯
    0.40
    䀓
    0.39
     *_
    0.39
     deciding
    0.38
     He
    0.38
     fault
    0.38
     decide
    0.37
    POSITIVE LOGITS
     unimagin
    0.50
    arsipkan
    0.50
    ⵡ
    0.49
     весьма
    0.48
    krom
    0.48
     來
    0.47
     ベージュ
    0.46
    besie
    0.46
     appreciably
    0.46
     fracción
    0.46
    Activations Density 0.000%

    No Known Activations