© 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-16K
    7. 10459
    Prev
    Next
    INDEX
    Explanations

    difference between

    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_16k_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
    ন
    1.95
     οποίο
    1.72
    IN
    1.66
    ные
    1.66
    Pair
    1.61
    ных
    1.59
     vær
    1.56
     Instru
    1.54
     coeffs
    1.50
    িক
    1.46
    POSITIVE LOGITS
    ра
    1.92
    すすめ
    1.79
    مل
    1.76
    oresis
    1.73
    at
    1.70
    ا
    1.68
    г
    1.65
    tır
    1.63
    ла
    1.58
    с
    1.56
    Activations Density 0.071%

    No Known Activations