© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    numbers like 4 followed by unit

    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
    AssetDiscovery
    0.72
    ева
    0.61
    ubwa
    0.59
    ور
    0.58
    тың
    0.57
    <unused1115>
    0.57
     água
    0.55
     SrvGroup
    0.55
    multiSelectList
    0.54
    vaegir
    0.54
    POSITIVE LOGITS
    G
    0.75
    n
    0.74
    し
    0.74
    r
    0.73
    4
    0.73
    c
    0.71
    ;
    0.70
    Set
    0.69
    *
    0.68
    ن
    0.68
    Activations Density 0.087%

    No Known Activations