© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    Islam and Muhammad

    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
    ו
    1.79
    IL
    1.66
    ло
    1.65
    rbrakk
    1.49
    وو
    1.46
    يسي
    1.43
    ור
    1.40
    e
    1.40
    檛
    1.39
    Callories
    1.37
    POSITIVE LOGITS
    ag
    1.77
    考えて
    1.75
    ী
    1.71
    ًا
    1.70
     tịch
    1.67
    ام
    1.59
    ेट
    1.58
     happenings
    1.58
    ϲ
    1.58
     Ə
    1.55
    Activations Density 0.033%

    No Known Activations