© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37321
    Prev
    Next
    INDEX
    Explanations

    expected value, minimizing, focus

    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
    отно
    0.43
    ваться
    0.43
    人格
    0.42
    胼
    0.42
    irradiated
    0.42
    发放
    0.41
    鱻
    0.41
     extrapolate
    0.41
    嘣
    0.41
    体内
    0.41
    POSITIVE LOGITS
     brochure
    0.54
     doesn
    0.48
     goalie
    0.48
    es
    0.46
    timezone
    0.45
     Penal
    0.45
    ru
    0.44
    pen
    0.44
     isn
    0.44
     Mur
    0.44
    Activations Density 0.004%

    No Known Activations