© 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. 11087
    Prev
    Next
    INDEX
    Explanations

    attempted to do

    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
    ،
    0.96
    P
    0.93
    وون
    0.89
    ри
    0.82
    UM
    0.80
    X
    0.79
     wider
    0.77
    牘
    0.75
    T
    0.74
    :
    0.74
    POSITIVE LOGITS
    ের
    0.80
     ولم
    0.80
     volna
    0.78
    s
    0.78
     وكانت
    0.75
    sila
    0.70
    Surname
    0.70
    ों
    0.70
    and
    0.69
     וש
    0.68
    Activations Density 0.034%

    No Known Activations