© 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. 94890
    Prev
    Next
    INDEX
    Explanations

    fishing spots

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

    biotic factors, Framework, directly holding, confidence

    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
    kov
    0.54
    (
    0.46
    ialize
    0.46
    ,
    0.45
     div
    0.43
    wwww
    0.42
    तीर्ण
    0.42
    WP
    0.41
    ;
    0.41
    forcer
    0.41
    POSITIVE LOGITS
     кисло
    0.57
    際は
    0.57
     музей
    0.54
     ル
    0.53
    ものは
    0.53
     当
    0.51
     akibat
    0.50
     は
    0.50
    ప్పుడు
    0.50
     酸
    0.50
    Activations Density 0.000%

    No Known Activations