© 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. 40568
    Prev
    Next
    INDEX
    Explanations

    business and technical configurations

    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
    妳
    0.42
     느끼
    0.42
    ⮚
    0.42
    咒
    0.42
    옅
    0.41
    ிறார்
    0.41
    忆
    0.41
    ٥
    0.41
     감소
    0.40
    嘿
    0.39
    POSITIVE LOGITS
    ie
    0.59
    ofthe
    0.53
    ov
    0.48
    ul
    0.47
     taking
    0.46
     enjoys
    0.46
    ption
    0.46
     enjoyed
    0.45
    on
    0.45
     terbaru
    0.45
    Activations Density 0.017%

    No Known Activations