© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    pull this off

    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
    cind
    2.16
    y
    2.11
     ομά
    2.00
     thiệu
    1.95
    ra
    1.91
    ta
    1.91
    ی
    1.81
    yog
    1.79
    קט
    1.73
    yon
    1.72
    POSITIVE LOGITS
    ógica
    1.73
    ล์
    1.66
    শনের
    1.64
    ivating
    1.63
    ωνα
    1.63
    ্পনিক
    1.58
    ักษณะ
    1.57
     disminuir
    1.55
    ა
    1.55
     וא
    1.54
    Activations Density 0.013%

    No Known Activations