© 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. 135125
    Prev
    Next
    INDEX
    Explanations

    new information and comparisons

    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
     ક્ષ
    0.59
     ժ
    0.52
    𒋼
    0.51
     formulario
    0.50
     ዘዴ
    0.50
     ფორ
    0.49
     qí
    0.48
    渶
    0.48
     Matemática
    0.48
     númer
    0.47
    POSITIVE LOGITS
     secretion
    0.51
    -
    0.51
     secretions
    0.46
    annon
    0.44
     chutes
    0.44
    ack
    0.43
     regulating
    0.42
     patterned
    0.42
     production
    0.41
     systems
    0.41
    Activations Density 0.003%

    No Known Activations