© 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-262K
    7. 802
    Prev
    Next
    INDEX
    Explanations

    is a/an

    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_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
    p
    2.11
    س
    1.99
    т
    1.81
    c
    1.65
    o
    1.59
    Р
    1.58
    t
    1.57
    to
    1.55
    ت
    1.53
    же
    1.51
    POSITIVE LOGITS
    하다
    1.63
    时候
    1.61
    ătur
    1.58
    piratory
    1.55
    िरा
    1.41
    AYLOR
    1.40
    ulnerable
    1.40
    KindOfClass
    1.40
    ogonal
    1.39
    ারী
    1.39
    Activations Density 1.104%

    No Known Activations