© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2946
    Prev
    Next
    INDEX
    Explanations

    about and related inquiries

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ك
    0.37
    lyrics
    0.28
    ج
    0.28
     dizendo
    0.27
    ۔
    0.26
    Untuk
    0.26
     Announces
    0.26
    Clik
    0.25
     mostrando
    0.25
    endere
    0.25
    POSITIVE LOGITS
    n
    0.33
    in
    0.29
    :
    0.27
     how
    0.27
     about
    0.27
    如何
    0.27
     bevorzug
    0.26
    这种情况
    0.25
    被
    0.25
     unfair
    0.24
    Activations Density 0.042%

    No Known Activations