© 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. 128565
    Prev
    Next
    INDEX
    Explanations

    capitalized words after 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
     &=&
    -1.03
    にほんブログ村
    -1.00
    Übersicht
    -0.93
     alors
    -0.93
    woff
    -0.92
    ごちそうさまでした
    -0.91
     Não
    -0.91
     these
    -0.90
    Beispiele
    -0.90
    Preise
    -0.85
    POSITIVE LOGITS
     his
    1.10
     participate
    1.01
     he
    0.99
     its
    0.99
     kanyang
    0.91
     involvement
    0.90
     außerdem
    0.85
     participated
    0.84
     to
    0.84
    ่วม
    0.83
    Activations Density 0.024%

    No Known Activations