© 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. 9385
    Prev
    Next
    INDEX
    Explanations

    gender identity

    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
     séquence
    0.46
     دماغ
    0.45
     sequência
    0.44
    ेशंस
    0.43
     ތ
    0.43
     sey
    0.41
     penuh
    0.40
     duduk
    0.40
     gelten
    0.40
    朓
    0.39
    POSITIVE LOGITS
     Achilles
    0.41
    rug
    0.40
     blocked
    0.40
     המס
    0.40
     eu
    0.40
     boxes
    0.39
    én
    0.39
     wound
    0.38
     materials
    0.38
     material
    0.37
    Activations Density 0.001%

    No Known Activations