© 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. 26877
    Prev
    Next
    INDEX
    Explanations

    step by step, break down

    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
    in
    0.38
     Financ
    0.33
     Weekend
    0.32
     Hotel
    0.32
     бушлай
    0.32
    k
    0.32
    Еще
    0.31
    ilah
    0.31
     Nietzsche
    0.31
     Journalist
    0.31
    POSITIVE LOGITS
    IENCE
    0.39
     equaling
    0.38
    。
    0.38
    :“
    0.37
     thresholds
    0.36
    ូត
    0.36
    َان
    0.36
     geometrical
    0.36
    ្នែក
    0.36
    ួក
    0.36
    Activations Density 0.001%

    No Known Activations