© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81355
    Prev
    Next
    INDEX
    Explanations

    kilogram of anything, table tennis, accidental presses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ড
    0.50
    ני
    0.49
    BUSINESS
    0.48
     scint
    0.47
    ด
    0.47
    ד
    0.47
    ורי
    0.46
    דות
    0.46
    AZIONE
    0.46
     azione
    0.45
    POSITIVE LOGITS
     erythematosus
    0.46
     များ
    0.45
     effectués
    0.43
    flops
    0.42
    throwing
    0.42
     (
    0.42
    attacking
    0.41
     பயணிகள்
    0.41
     trường
    0.41
    hoff
    0.40
    Activations Density 0.004%

    No Known Activations