© 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. 11829
    Prev
    Next
    INDEX
    Explanations

    names starting with E, K, P, H, B

    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
     toute
    1.19
    Мы
    1.13
     Toutefois
    1.10
     οπο
    1.07
     unclear
    1.05
    C
    1.05
    вать
    1.03
    อื่นๆ
    1.03
    Más
    1.00
     quelqu
    0.97
    POSITIVE LOGITS
    いた
    2.05
    り
    1.79
    theless
    1.63
    니다
    1.60
    서
    1.55
    shire
    1.54
    tedir
    1.53
    oretically
    1.45
    ান
    1.40
    ారు
    1.39
    Activations Density 0.011%

    No Known Activations