© 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. 116257
    Prev
    Next
    INDEX
    Explanations

    resource leakssimilar products/servicesclients and departmentsmathematical formulasdirect competitors

    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
     अन्य
    0.74
    ાન
    0.70
    靂
    0.68
    ᱔
    0.68
    याम
    0.68
    下載
    0.67
     liye
    0.65
    मिया
    0.64
     म्यूजिक
    0.63
     टिप्स
    0.63
    POSITIVE LOGITS
     혹은
    0.98
     상
    0.93
     가
    0.93
    어
    0.91
    거
    0.91
     생각
    0.89
     슬
    0.89
     거
    0.88
     상황
    0.88
     직접
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.