© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11802
    Prev
    Next
    INDEX
    Explanations

    aka definition

    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
    ك
    1.90
    től
    1.81
    ia
    1.62
    ное
    1.62
    hai
    1.55
    lo
    1.52
    ية
    1.51
    ৬
    1.48
    ность
    1.45
    ном
    1.36
    POSITIVE LOGITS
    س
    1.60
    e
    1.50
    aş
    1.41
     considerados
    1.38
     speelt
    1.37
     অপরের
    1.35
     especializados
    1.33
     склады
    1.33
     stanje
    1.33
    o
    1.32
    Activations Density 0.000%

    No Known Activations