© 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. 21989
    Prev
    Next
    INDEX
    Explanations

    Fridays, seed

    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
     {
    0.51
    INCREMENT
    0.48
     category
    0.45
     Increase
    0.45
     Grammar
    0.43
    Increase
    0.43
     sari
    0.43
     File
    0.43
     ק
    0.43
     Literature
    0.43
    POSITIVE LOGITS
    den
    0.46
    odt
    0.44
    بد
    0.42
    dR
    0.41
     بالت
    0.41
    penas
    0.40
    bought
    0.39
    eden
    0.39
    стема
    0.39
    មុ
    0.39
    Activations Density 0.001%

    No Known Activations