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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12276
    Prev
    Next
    INDEX
    Explanations

    sentence ending 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_10/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
     sobot
    -1.98
     listop
    -1.98
     čaj
    -1.97
     klubu
    -1.94
     serca
    -1.93
     parku
    -1.84
     Otros
    -1.83
     poby
    -1.81
     Lleg
    -1.81
    ⃢
    -1.79
    POSITIVE LOGITS
     is
    2.27
     also
    2.02
     your
    1.99
     with
    1.96
     in
    1.92
     still
    1.85
     was
    1.83
    U
    1.80
     even
    1.80
     didn
    1.79
    Activations Density 0.028%

    No Known Activations