© 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. 40396
    Prev
    Next
    INDEX
    Explanations

    strictly avoid or prohibit

    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
     réfl
    1.90
    と思います
    1.84
    ية
    1.82
    र्जर
    1.82
    씀
    1.80
     quantas
    1.78
    𝕝
    1.78
    ဉ်
    1.76
    られて
    1.73
     그런데
    1.73
    POSITIVE LOGITS
    ments
    2.06
    साठी
    1.95
    จะ
    1.78
    亠
    1.73
     fibroblasts
    1.59
    要想
    1.59
     confidential
    1.59
    نا
    1.58
    rooms
    1.56
    \,\
    1.55
    Activations Density 0.010%

    No Known Activations