© 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. 163738
    Prev
    Next
    INDEX
    Explanations

    Detector Watch Face

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

    anything else

    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
    er
    0.51
    liği
    0.50
    anova
    0.49
    ö
    0.49
     свой
    0.48
    ight
    0.48
    hov
    0.48
    angel
    0.47
    ጡ
    0.47
    en
    0.47
    POSITIVE LOGITS
     excessive
    0.53
     கடவு
    0.52
     PIPE
    0.44
    ポケモン
    0.43
     MUL
    0.43
    クマ
    0.42
     spectacles
    0.41
     PERFORMANCE
    0.41
     Excessive
    0.41
    き
    0.41
    Activations Density 0.000%

    No Known Activations