© 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. 9377
    Prev
    Next
    INDEX
    Explanations

    two weeks' notice

    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
     outcrops
    0.41
     modulate
    0.41
     ንጥረ
    0.41
     utilisent
    0.41
     strobe
    0.41
    在地
    0.41
     Ау
    0.41
    ಸೂ
    0.40
    秒
    0.40
     manip
    0.40
    POSITIVE LOGITS
     farewell
    1.19
     resignation
    1.00
     leaving
    0.99
     Farewell
    0.97
     resigning
    0.96
     meninggalkan
    0.95
     Leaving
    0.90
     goodbye
    0.90
     resign
    0.88
     resigned
    0.87
    Activations Density 0.092%

    No Known Activations