© 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. 3786
    Prev
    Next
    INDEX
    Explanations

    index followed by =, funds, out, names, or tracking

    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
    ص
    2.19
    с
    1.88
    ната
    1.72
     EUROPE
    1.69
    ě
    1.68
    叭
    1.68
     considéré
    1.66
    기
    1.66
    쏜
    1.66
     چنان
    1.62
    POSITIVE LOGITS
    dır
    2.92
    gew
    2.23
    gruppe
    2.20
    gruppen
    2.14
    gru
    2.09
    gp
    1.96
    gerät
    1.91
    𝙨
    1.91
    guo
    1.90
    𝙜
    1.89
    Activations Density 0.018%

    No Known Activations