© 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. 6826
    Prev
    Next
    INDEX
    Explanations

    coding libraries and technical terms

    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
    ی
    2.78
    ان
    2.77
    aient
    2.67
    eer
    2.53
    aan
    2.52
    েই
    2.50
    aa
    2.47
    ात
    2.44
    ال
    2.39
    اس
    2.31
    POSITIVE LOGITS
    ずっと
    1.84
    ไม่
    1.82
    하여
    1.82
     攵
    1.74
    ্পনিক
    1.74
     tệ
    1.73
    다는
    1.72
    다고
    1.71
    lytres
    1.68
     bodied
    1.68
    Activations Density 0.068%

    No Known Activations