© 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. 11804
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    𝑍
    0.86
    malt
    0.83
    к
    0.81
    ن
    0.79
    script
    0.79
     maravill
    0.78
    𝑙
    0.78
    ഷി
    0.77
    benzoimidazol
    0.76
    Ｄ
    0.76
    POSITIVE LOGITS
    ่
    0.95
    শ্বর
    0.92
     isolation
    0.79
     singularity
    0.77
     insertion
    0.75
     preventable
    0.75
     deletion
    0.75
     enforce
    0.74
     evasion
    0.74
     invasion
    0.73
    Activations Density 0.000%

    No Known Activations