© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8296
    Prev
    Next
    INDEX
    Explanations

    as a

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

    as a large language model

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     heroes
    0.57
     героев
    0.54
     геро
    0.52
     ஹீரோ
    0.46
     hero
    0.46
     Heroes
    0.45
     Hero
    0.45
     héro
    0.44
    }}^
    0.43
     heroism
    0.41
    POSITIVE LOGITS
    身为
    0.69
     outsider
    0.67
     jestem
    0.64
    늙
    0.61
     skeptic
    0.60
     nerdy
    0.59
     marketer
    0.57
     myself
    0.57
    🙋
    0.57
     skeptical
    0.55
    Activations Density 0.327%

    No Known Activations