© 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. 80257
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations

    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
    뷊
    0.54
    䡉
    0.50
     seminar
    0.48
     riser
    0.48
     notor
    0.48
     cine
    0.48
     ram
    0.47
     čak
    0.46
     sheaf
    0.46
     zabaw
    0.46
    POSITIVE LOGITS
    uity
    0.49
    ie
    0.48
    utions
    0.47
    iones
    0.47
    2
    0.46
    os
    0.45
    ore
    0.44
    *\
    0.44
    orie
    0.43
    Offline
    0.43
    Activations Density 0.000%

    No Known Activations