© 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. 38852
    Prev
    Next
    INDEX
    Explanations

    amount preceded by $

    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
    ן
    0.63
    ater
    0.47
    gling
    0.47
    ia
    0.46
     de
    0.46
    ék
    0.46
    ↵↵
    0.45
    p
    0.45
    nal
    0.44
    na
    0.44
    POSITIVE LOGITS
     دور
    0.48
    ضع
    0.47
     شن
    0.47
     賞
    0.45
    RAchievement
    0.43
     tierras
    0.43
    僮
    0.43
    ккей
    0.42
    $...
    0.42
     Burch
    0.42
    Activations Density 0.001%

    No Known Activations