© 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. 20991
    Prev
    Next
    INDEX
    Explanations

    formulas and variables

    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
     মেঝে
    0.45
    áreas
    0.44
    oy
    0.43
    obedience
    0.43
    farin
    0.42
     fundamento
    0.42
    ohn
    0.41
    峯
    0.41
    ôté
    0.40
    ikut
    0.40
    POSITIVE LOGITS
    prisingly
    0.47
     escenarios
    0.44
     realista
    0.44
    SIZE
    0.42
    ্রে
    0.41
     realistic
    0.40
    Realistic
    0.40
     Resources
    0.40
    ्र
    0.39
    ಸ್‌
    0.39
    Activations Density 0.000%

    No Known Activations