© 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. 109439
    Prev
    Next
    INDEX
    Explanations

    essential humansurvival

    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
     BES
    0.44
    aw
    0.42
    慈善
    0.42
    path
    0.42
    lossen
    0.41
    sponsored
    0.41
     путь
    0.40
    op
    0.40
    लीवुड
    0.40
     $+
    0.39
    POSITIVE LOGITS
     Ainda
    0.51
     Profil
    0.50
     După
    0.49
     Após
    0.48
    İ
    0.45
     फक्त
    0.45
     fluctuates
    0.45
     veloc
    0.44
     февра
    0.44
    蜈
    0.44
    Activations Density 0.002%

    No Known Activations