© 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. 34529
    Prev
    Next
    INDEX
    Explanations

    Tax, gov, oodle, Big, Puppy, impact

    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
    Negative Logits
     pung
    0.77
    ে
    0.76
     χρόνια
    0.75
    iunea
    0.73
     haies
    0.68
    錤
    0.68
     mensual
    0.68
     dinyatakan
    0.67
    δά
    0.67
    ಗಳಲ್ಲಿ
    0.65
    POSITIVE LOGITS
    ian
    0.91
    vian
    0.85
     Saves
    0.84
     Writes
    0.84
    舟
    0.80
    asibility
    0.79
    .—
    0.77
    之为
    0.74
    ance
    0.73
    льной
    0.73
    Activations Density 0.001%

    No Known Activations