© 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-16K
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    touch of

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    1.26
    packages
    1.16
    ه
    1.10
    ↵↵
    1.00
    movies
    0.97
    g
    0.97
    ים
    0.96
    purch
    0.96
    i
    0.96
    í
    0.96
    POSITIVE LOGITS
    ,_-
    1.22
     ionization
    1.15
     standardization
    1.14
     elegance
    1.13
     intención
    1.13
     photometric
    1.13
     flair
    1.10
     modulation
    1.09
     hemodynamic
    1.09
     neutrophil
    1.09
    Activations Density 0.160%

    No Known Activations