© 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. 80737
    Prev
    Next
    INDEX
    Explanations

    subjective assessment

    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
    Python
    0.47
     Kunststoff
    0.47
    re
    0.46
    algorithm
    0.44
     Mycobacterium
    0.44
    By
    0.43
    receptor
    0.43
    或
    0.43
    äre
    0.43
    Plastic
    0.43
    POSITIVE LOGITS
    狽
    0.45
     ridiculous
    0.44
     statunit
    0.42
     χρώ
    0.42
     imen
    0.42
     iar
    0.41
     illustrious
    0.41
     senc
    0.40
     jolie
    0.40
     دسته
    0.40
    Activations Density 0.006%

    No Known Activations