© 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. 8657
    Prev
    Next
    INDEX
    Explanations

    Rewrite or modify

    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
    ज
    0.52
    м
    0.51
    不论
    0.50
    म
    0.50
    سی
    0.50
    ث
    0.48
    ש
    0.47
    حضرت
    0.46
    ंग
    0.46
    어
    0.44
    POSITIVE LOGITS
     desenhos
    0.48
    ные
    0.45
     здания
    0.44
     nacionais
    0.44
     slogans
    0.43
    urados
    0.43
    ars
    0.43
    swire
    0.43
    ivated
    0.43
     invoices
    0.42
    Activations Density 0.582%

    No Known Activations