© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    id followed by SERIAL or INT

    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
    iu
    1.16
    était
    1.16
    ě
    1.10
    ين
    1.09
    ம்
    1.04
    ні
    1.04
    iance
    1.04
    ić
    1.04
    Caractéristiques
    1.03
    ו
    1.02
    POSITIVE LOGITS
     осуществляется
    1.04
     используют
    1.02
    ség
    1.02
     зависит
    1.01
     하다
    0.98
    쭉
    0.96
    あります
    0.95
    வதேச
    0.95
    ς
    0.94
     основным
    0.92
    Activations Density 0.008%

    No Known Activations