© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85655
    Prev
    Next
    INDEX
    Explanations

    special kinds of things

    np_acts-logits-general · gemini-2.5-flash-lite

    special and its common follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ك
    0.89
    S
    0.82
    N
    0.80
    }$
    0.78
    O
    0.75
    1
    0.70
    Sk
    0.68
    H
    0.67
    ะ
    0.66
     arbets
    0.66
    POSITIVE LOGITS
    special
    1.51
    特別な
    1.33
     especiais
    1.30
     특별
    1.30
    pecial
    1.16
     spéciales
    1.16
     специальных
    1.16
     ವಿಶೇಷ
    1.16
    特殊
    1.15
     speciale
    1.14
    Activations Density 0.091%

    No Known Activations