© 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. 11868
    Prev
    Next
    INDEX
    Explanations

    avoid generating content

    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
     ischa
    1.50
    ल
    1.40
     związ
    1.38
     enkelt
    1.37
     exposé
    1.35
     avoidable
    1.33
     பெறும்
    1.27
     ischemic
    1.26
     invariants
    1.25
     Alloy
    1.22
    POSITIVE LOGITS
    Фе
    1.70
    ად
    1.69
    c
    1.66
    将
    1.65
    ות
    1.62
    på
    1.62
    ע
    1.59
    ع
    1.59
    arad
    1.57
    ot
    1.56
    Activations Density 0.032%

    No Known Activations