© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47443
    Prev
    Next
    INDEX
    Explanations

    card ranks and suits

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ρία
    0.41
    靶
    0.41
     bluff
    0.39
     swims
    0.39
    equivalence
    0.37
     octa
    0.37
     thinning
    0.37
     infus
    0.37
     தீர்
    0.36
     equivalence
    0.36
    POSITIVE LOGITS
    hetes
    0.47
     posición
    0.43
    綏
    0.43
     posição
    0.42
    Position
    0.41
     Position
    0.39
     ಪೂರ್ವ
    0.39
     tịch
    0.39
     Hij
    0.38
     Blind
    0.38
    Activations Density 0.011%

    No Known Activations