© 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. 40-GEMMASCOPE-2-RES-262K
    4. 111141
    Prev
    Next
    INDEX
    Explanations

    numbers and dates in legal citations

    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_40_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
     മാര്‍
    0.40
    zień
    0.39
    户
    0.38
    柠
    0.37
    ък
    0.37
     名称
    0.37
    生产
    0.37
     دیتا
    0.37
    ضور
    0.36
    点了
    0.36
    POSITIVE LOGITS
     sendiri
    0.39
    ᑕ
    0.39
     ange
    0.38
     bei
    0.37
    фа
    0.37
    RESEARCH
    0.37
     nella
    0.37
     Vs
    0.36
    CTION
    0.36
     halk
    0.36
    Activations Density 0.002%

    No Known Activations