© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26916
    Prev
    Next
    INDEX
    Explanations

    Executive summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    achy
    0.45
     QSO
    0.39
     directive
    0.38
     associative
    0.38
     silos
    0.38
     wheelbase
    0.38
     अवसरों
    0.37
     ingredient
    0.37
    坯
    0.37
     fund
    0.36
    POSITIVE LOGITS
    А
    0.41
     heredit
    0.39
    BatchNorm
    0.36
    出血
    0.36
     Cricket
    0.35
    Cricket
    0.35
    阿
    0.35
    厚生
    0.35
     Blessed
    0.35
    文本
    0.34
    Activations Density 0.000%

    No Known Activations