© 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-65K
    7. 44814
    Prev
    Next
    INDEX
    Explanations

    process limits

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    퐫
    0.52
    siehe
    0.48
    Siehe
    0.45
    誇
    0.45
    เครื่อง
    0.44
    <0xA8>
    0.44
    秚
    0.44
    บุรี
    0.43
    ၷ
    0.43
     gereken
    0.43
    POSITIVE LOGITS
    _
    0.52
     troops
    0.46
    ;)
    0.45
    ல்
    0.45
     Counseling
    0.43
     ఏం
    0.42
     Tri
    0.42
    ;.
    0.41
    jans
    0.41
     धर्मा
    0.41
    Activations Density 0.003%

    No Known Activations