© 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. 10756
    Prev
    Next
    INDEX
    Explanations

    data field names

    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
    Negative Logits
     avevano
    0.91
    一個
    0.89
    
    0.88
    ців
    0.88
    𝘼
    0.86
    镓
    0.86
    榈
    0.85
     якщо
    0.84
     ниво
    0.84
     projectiles
    0.84
    POSITIVE LOGITS
    op
    0.93
     للغاية
    0.83
    ast
    0.82
    ient
    0.80
    le
    0.79
    er
    0.79
    e
    0.79
    s
    0.78
    didn
    0.77
    ident
    0.76
    Activations Density 0.197%

    No Known Activations