© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133712
    Prev
    Next
    INDEX
    Explanations

    remaining exhaust, distance, year, effect

    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_40_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
    աք
    0.40
    すぐに
    0.39
     আশে
    0.38
    雩
    0.38
    CTION
    0.38
    ابات
    0.37
    getAsJsonObject
    0.37
    isms
    0.36
     bodies
    0.36
    ́
    0.36
    POSITIVE LOGITS
     Dalton
    0.41
     rc
    0.40
     dirty
    0.39
     заказа
    0.39
     स्ट्रीट
    0.39
    raut
    0.38
    έα
    0.38
     street
    0.38
     attendance
    0.38
     दोनों
    0.38
    Activations Density 0.000%

    No Known Activations