© 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. 40448
    Prev
    Next
    INDEX
    Explanations

    Python code and data structures

    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
    ס
    1.53
     tomography
    1.34
    வும்
    1.33
    '{
    1.32
    xima
    1.25
    sizer
    1.20
    ことにより
    1.20
    ።
    1.19
     the
    1.16
    '-
    1.15
    POSITIVE LOGITS
    Й
    1.62
    ТИ
    1.42
    VENTION
    1.41
    М
    1.40
    어
    1.34
    Н
    1.34
    기
    1.33
    С
    1.31
    З
    1.31
    Т
    1.29
    Activations Density 0.001%

    No Known Activations