© 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. 9093
    Prev
    Next
    INDEX
    Explanations

    aims for classic

    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
     Snapdragon
    0.49
     Teilnehmer
    0.46
     الأحمر
    0.46
    闼
    0.46
    ступ
    0.45
    ötzlich
    0.45
    পণ
    0.44
     Quadrup
    0.44
     விழா
    0.44
     drywall
    0.44
    POSITIVE LOGITS
    customize
    0.48
    lette
    0.43
    _{\
    0.43
     savoir
    0.43
     classics
    0.42
     briefing
    0.42
     vibes
    0.42
    eling
    0.42
    uning
    0.42
    vre
    0.41
    Activations Density 0.002%

    No Known Activations