© 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. 40927
    Prev
    Next
    INDEX
    Explanations

    general information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     промышленности
    0.47
     ఆదేశ
    0.45
     etiqu
    0.44
    ның
    0.43
    吅
    0.43
    原因
    0.42
     аўтаматы
    0.42
     Trabajo
    0.41
     méthod
    0.41
    гото
    0.41
    POSITIVE LOGITS
    k
    0.45
    axis
    0.43
    eq
    0.43
    generators
    0.43
    cheese
    0.41
     purchasers
    0.41
    generate
    0.41
    per
    0.40
    hope
    0.40
     dances
    0.39
    Activations Density 0.004%

    No Known Activations