© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    java imports and semicolons

    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
    addena
    0.41
     एक्सरसा
    0.39
    <unused40>
    0.39
     शौचालय
    0.38
    cevam
    0.38
     نیست
    0.37
    柺
    0.36
     शौचाल
    0.36
     شما
    0.36
    akaranam
    0.36
    POSITIVE LOGITS
    <0x0D>
    0.46
    ;
    0.46
    _
    0.42
    ↵↵
    0.41
    Factory
    0.41
    ,
    0.41
    ↵
    0.40
    ↵↵↵
    0.40
    Q
    0.40
    -
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.