© 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-65K
    7. 65240
    Prev
    Next
    INDEX
    Explanations

    evaluating degree or importance

    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_65k_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
    选项
    0.58
    马
    0.57
     הוא
    0.54
     추가
    0.54
     मिश्रा
    0.53
     other
    0.53
    า
    0.52
    <unused260>
    0.52
    ק
    0.51
     לא
    0.51
    POSITIVE LOGITS
    -,
    0.54
     poverty
    0.54
     pobreza
    0.52
     neurotic
    0.49
    기와
    0.49
    したり
    0.48
     maupun
    0.47
     fuelwood
    0.46
     disequ
    0.45
     bivariate
    0.44
    Activations Density 0.025%

    No Known Activations