© 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. 237408
    Prev
    Next
    INDEX
    Explanations

    Write, results, suggested, violations

    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
    OVERRIDES
    0.46
    Fed
    0.44
    Army
    0.43
    aggregation
    0.43
     wrestling
    0.41
     investing
    0.41
    大學
    0.41
    軍
    0.41
    閱讀
    0.41
    많은
    0.41
    POSITIVE LOGITS
     newfound
    0.52
     તેમને
    0.46
     donned
    0.46
    getline
    0.45
     demiş
    0.45
     retrouver
    0.44
     theyre
    0.44
     politely
    0.44
     nieuwe
    0.44
     আসছে
    0.44
    Activations Density 0.001%

    No Known Activations