© 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. 200221
    Prev
    Next
    INDEX
    Explanations

    recognizes otherness

    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
    ﻑ
    0.43
    ۇ
    0.42
     easily
    0.41
     .
    0.41
     at
    0.41
     echo
    0.41
    вне
    0.40
     I
    0.40
     travels
    0.40
     supposedly
    0.40
    POSITIVE LOGITS
     തിരിച്ച
    0.48
     décider
    0.45
    ovington
    0.44
    ajt
    0.44
     zez
    0.44
     раху
    0.43
    ឃើញ
    0.43
     Oké
    0.43
     mannen
    0.43
    alade
    0.42
    Activations Density 0.004%

    No Known Activations