© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2984
    Prev
    Next
    INDEX
    Explanations

    or

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    eduanya
    0.40
     auspicious
    0.39
    ക്കിയത്
    0.38
     टीस्पून
    0.38
     že
    0.38
    썹
    0.37
    💋
    0.37
    tuvo
    0.37
    ണമെന്ന്
    0.37
    etku
    0.36
    POSITIVE LOGITS
     или
    0.82
     veya
    0.73
    或其他
    0.71
     அல்லது
    0.71
     किंवा
    0.71
     hoặc
    0.70
    或
    0.70
     또는
    0.68
     અથવા
    0.66
     లేదా
    0.65
    Activations Density 0.116%

    No Known Activations