© 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. 2336
    Prev
    Next
    INDEX
    Explanations

    find outlines and depth

    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
    ⦿
    0.47
    opolymers
    0.46
     मिनिस्टर
    0.46
    u
    0.46
     खोली
    0.46
     கல்லற
    0.44
     MADE
    0.44
     özellikle
    0.44
     преде
    0.43
     লীগ
    0.43
    POSITIVE LOGITS
    žiť
    0.47
    一股
    0.45
    şık
    0.44
    ቅር
    0.44
    idia
    0.43
    ᅵ
    0.43
    Pit
    0.42
     trope
    0.42
    ུང་
    0.42
    기고
    0.42
    Activations Density 0.000%

    No Known Activations