© 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. 56138
    Prev
    Next
    INDEX
    Explanations

    organization categories and advice

    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
     Spin
    0.50
     anys
    0.47
     Dian
    0.43
     Notas
    0.43
     licenciado
    0.40
    зино
    0.40
     Chaud
    0.39
    ленного
    0.39
     siglos
    0.39
    :}
    0.38
    POSITIVE LOGITS
    ATP
    0.43
    space
    0.42
     tallest
    0.42
    Shelf
    0.42
    Subtraction
    0.42
    uke
    0.41
     shelves
    0.39
    OL
    0.39
     fastening
    0.39
    älle
    0.38
    Activations Density 0.007%

    No Known Activations