© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1980
    Prev
    Next
    INDEX
    Explanations

    fermented soybean paste or distance between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    跋
    0.78
     method
    0.74
     despatch
    0.68
     omissions
    0.67
    riev
    0.67
     +=
    0.67
     Enlarg
    0.65
     system
    0.65
     Greeley
    0.63
     congrat
    0.63
    POSITIVE LOGITS
     oreille
    1.44
    Spark
    1.35
     volante
    1.35
    Pearl
    1.34
     MUSE
    1.34
     божомолдору
    1.33
     starters
    1.32
    足球
    1.31
    duck
    1.31
    奭
    1.29
    Activations Density 0.983%

    No Known Activations