© 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. 238600
    Prev
    Next
    INDEX
    Explanations

    illegal entities, SCAN Monitor

    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
     (
    0.55
     TD
    0.50
     INTO
    0.48
     G
    0.48
     E
    0.47
     &
    0.45
     Opinion
    0.45
     Innovation
    0.45
     Morgan
    0.44
     Ν
    0.44
    POSITIVE LOGITS
    忶
    0.49
     esforços
    0.47
    葱
    0.47
    repetitions
    0.46
    र्डर
    0.46
    جهز
    0.45
    黴
    0.45
    描写
    0.45
     milliam
    0.45
    踌
    0.44
    Activations Density 0.000%

    No Known Activations