© 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. 173510
    Prev
    Next
    INDEX
    Explanations

    cleaning, supplier, skirts, empty, out

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

    definition, rename, requests

    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
     J
    0.45
     வீட்டு
    0.44
    ายเป็น
    0.43
    踢
    0.42
     Sper
    0.41
     =
    0.41
    აში
    0.40
     sper
    0.40
     Shimano
    0.39
    坷
    0.39
    POSITIVE LOGITS
    league
    0.48
     aspiring
    0.46
    🎪
    0.46
    UAE
    0.45
    venue
    0.44
     selepas
    0.44
     nền
    0.44
    yspace
    0.44
     overshadowed
    0.44
    ার্থী
    0.43
    Activations Density 0.000%

    No Known Activations