© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    sequence starters

    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
    Surely
    0.52
    asel
    0.51
     restaurantes
    0.50
     problemler
    0.50
    Depois
    0.49
     cherish
    0.49
    淔
    0.49
     stave
    0.47
    conect
    0.47
    НЕ
    0.46
    POSITIVE LOGITS
     Class
    0.51
     Rap
    0.48
     Broad
    0.46
     Audience
    0.46
     Midtown
    0.46
     >
    0.46
     SDK
    0.45
    Width
    0.45
    ścic
    0.44
    -
    0.44
    Activations Density 0.000%

    No Known Activations