© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25489
    Prev
    Next
    INDEX
    Explanations

    flights, term, executable option

    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
     gial
    0.52
     chewed
    0.50
    ă
    0.45
    หน้าที่
    0.44
    ο
    0.44
     grueling
    0.42
    ﻞ
    0.42
    早い
    0.42
    ικ
    0.41
     suficiente
    0.41
    POSITIVE LOGITS
    dbcontext
    0.50
     خص
    0.46
    oxine
    0.45
     இதன
    0.44
    itiveness
    0.44
    traditional
    0.43
    الس
    0.43
    বারের
    0.43
    क्षेत्र
    0.43
     الاست
    0.43
    Activations Density 0.003%

    No Known Activations