© 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. 44476
    Prev
    Next
    INDEX
    Explanations

    appcompat and app titles

    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
    SL
    0.67
    ):
    0.64
    `,
    0.62
    ',
    0.61
    SP
    0.61
    SC
    0.59
    ）,
    0.59
    ",
    0.58
    SE
    0.58
    B
    0.58
    POSITIVE LOGITS
     말투
    0.48
     অক্ষয়
    0.46
     문화
    0.46
    颌
    0.46
     하루
    0.44
    ਰ
    0.44
     شهرستان
    0.44
    ედერ
    0.43
     simplification
    0.43
    ೭
    0.43
    Activations Density 0.001%

    No Known Activations