© 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. 56362
    Prev
    Next
    INDEX
    Explanations

    fortune cookies, fortune tellers, 500

    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
    iffe
    0.43
    痫
    0.43
    薅
    0.41
    ftop
    0.40
    트를
    0.39
     inhuman
    0.39
    estructive
    0.39
     Kaufman
    0.39
    誑
    0.39
    ytale
    0.38
    POSITIVE LOGITS
     Industria
    0.45
     Fortune
    0.44
     coltiv
    0.43
     ৫০০
    0.43
     sekali
    0.42
     przedsiębior
    0.42
     voort
    0.42
     teller
    0.41
     cookie
    0.41
    Fortune
    0.41
    Activations Density 0.014%

    No Known Activations