© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26366
    Prev
    Next
    INDEX
    Explanations

    attribution punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FANDOM
    -1.13
    ровки
    -1.09
     ambos
    -1.06
    accéder
    -1.03
     caricatura
    -1.02
    тистика
    -1.02
     ингреди
    -1.00
     trofeo
    -0.99
    举动
    -0.98
     Wikip
    -0.97
    POSITIVE LOGITS
     xí
    1.01
     isolado
    0.94
     acresc
    0.94
     daquele
    0.91
     caminh
    0.90
    lettre
    0.90
    ukraine
    0.90
     who
    0.90
     elétrica
    0.88
    xiaomi
    0.88
    Activations Density 0.003%

    No Known Activations