© 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. 34834
    Prev
    Next
    INDEX
    Explanations

    safety and security

    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
     וש
    1.58
     таки
    1.41
     covers
    1.37
     dotycz
    1.36
    s
    1.30
     Globally
    1.23
     accordingly
    1.22
     acab
    1.20
    ের
    1.17
     habido
    1.17
    POSITIVE LOGITS
    ل
    2.27
    ان
    1.94
    മ
    1.87
    о
    1.84
    ك
    1.84
    ა
    1.80
    ка
    1.77
    り
    1.68
    ش
    1.67
    у
    1.66
    Activations Density 0.020%

    No Known Activations