© 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. 199976
    Prev
    Next
    INDEX
    Explanations

    connecting to smart devices

    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
     Scenic
    0.44
    རྒྱ
    0.42
    ↵
    0.42
     Daylight
    0.41
     фир
    0.41
    োর্
    0.40
     Casc
    0.40
     Flavor
    0.40
    𐰴
    0.40
    วันที่
    0.39
    POSITIVE LOGITS
    rar
    0.49
    romo
    0.49
    钊
    0.48
    istory
    0.48
     sociali
    0.48
    missione
    0.47
    rico
    0.45
     음악
    0.45
    ریت
    0.45
    ị
    0.45
    Activations Density 0.000%

    No Known Activations