© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99716
    Prev
    Next
    INDEX
    Explanations

    AI followed by institute, acronyms, or names

    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_34/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
    бенок
    -0.77
     bro
    -0.73
    вказ
    -0.71
     additions
    -0.68
     RR
    -0.66
     breastfeeding
    -0.66
    Uno
    -0.66
     AH
    -0.66
    人数
    -0.66
     downg
    -0.65
    POSITIVE LOGITS
    êng
    0.88
     Ai
    0.87
     Aix
    0.85
    Ais
    0.84
     Aig
    0.82
     aima
    0.80
     accueille
    0.79
     AIN
    0.78
     Tira
    0.78
     艾
    0.78
    Activations Density 0.034%

    No Known Activations