© 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. 45229
    Prev
    Next
    INDEX
    Explanations

    largely obsolete / replaced / superseded

    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
    ية
    1.84
    িক
    1.67
    ى
    1.62
    要知道
    1.57
     Provisions
    1.53
    ExpressCheckout
    1.52
    ્સ
    1.48
    ны
    1.47
     Това
    1.47
     Με
    1.46
    POSITIVE LOGITS
    м
    1.95
    ר
    1.84
    म
    1.82
    ル
    1.70
    ுகள்
    1.66
    <0x88>
    1.59
    ̀ng
    1.59
    ה
    1.58
    b
    1.56
    m
    1.52
    Activations Density 0.009%

    No Known Activations