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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41274
    Prev
    Next
    INDEX
    Explanations

    code formatting indicators

    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
    ารย์
    2.06
    ू
    2.05
     keď
    1.91
    ਨ
    1.88
     laureate
    1.88
    ेंट
    1.85
     größte
    1.78
    了一些
    1.76
     pokoj
    1.76
    ْم
    1.75
    POSITIVE LOGITS
    ي
    3.17
    lowing
    2.45
    માં
    2.36
    д
    2.34
    특별시
    2.28
    ك
    2.28
    gd
    2.23
    y
    2.23
    س
    2.19
    ik
    2.17
    Activations Density 0.004%

    No Known Activations