© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    tables with headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
    м
    2.69
    م
    2.52
    a
    1.99
    ン
    1.96
    an
    1.90
    ه
    1.88
    да
    1.83
    ن
    1.83
    m
    1.79
    i
    1.73
    POSITIVE LOGITS
    AK
    1.54
    APs
    1.49
    НЫ
    1.30
    ICAS
    1.28
    lov
    1.27
    ECs
    1.25
    tk
    1.24
    correct
    1.24
    reng
    1.24
    ISIS
    1.23
    Activations Density 0.037%

    No Known Activations