© 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. 8490
    Prev
    Next
    INDEX
    Explanations

    academic figures and names

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

    scientists and historical figures

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.44
    Treasurer
    0.44
    Cheat
    0.41
    コンピュー
    0.40
    㪯
    0.40
    道德
    0.39
    ChooseCharacter
    0.39
    MatContext
    0.39
     Colleen
    0.39
    Debbie
    0.39
    POSITIVE LOGITS
     academically
    0.60
     Akademie
    0.58
     von
    0.57
     Akadem
    0.57
     Hermann
    0.56
     Wilhelm
    0.56
     Transactions
    0.55
     academ
    0.55
     É
    0.54
     Heinrich
    0.53
    Activations Density 0.148%

    No Known Activations