© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1417
    Prev
    Next
    INDEX
    Explanations

    reaching a fever pitch

    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
    ^{\
    -1.30
    ра
    -1.30
     appelés
    -1.21
     sencillas
    -1.21
    ”-
    -1.21
     ‘’
    -1.20
     fontes
    -1.18
    Бележки
    -1.15
                       
    -1.14
     associés
    -1.14
    POSITIVE LOGITS
     in
    1.19
     отри
    1.17
    idikan
    1.13
    未能
    1.11
     consommation
    1.11
    int
    1.09
     possibility
    1.07
     kuat
    1.07
     visibility
    1.06
     القر
    1.06
    Activations Density 0.043%

    No Known Activations