© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 94
    Prev
    Next
    INDEX
    Explanations

    FastAPI imports

    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
    n
    3.39
    b
    2.03
    les
    1.90
    o
    1.88
    th
    1.83
    ni
    1.83
    y
    1.82
    h
    1.79
    d
    1.73
    p
    1.70
    POSITIVE LOGITS
    ת
    2.03
    부터
    1.84
    т
    1.75
    が必要
    1.72
    ция
    1.70
    ം
    1.66
     истины
    1.62
    のための
    1.61
    い
    1.61
    が多く
    1.60
    Activations Density 0.020%

    No Known Activations