© 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. 267
    Prev
    Next
    INDEX
    Explanations

    structured data formats

    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
     of
    -1.88
    5
    -1.42
     that
    -1.40
     such
    -1.38
    Beskrivning
    -1.37
    Transcripción
    -1.34
    Transkrypt
    -1.30
    Transcriptie
    -1.29
     larger
    -1.26
     ("
    -1.25
    POSITIVE LOGITS
     دولار
    1.35
    radiation
    1.34
     ')[
    1.34
    걍
    1.33
    寅
    1.33
    Nationalité
    1.31
    ivore
    1.30
     phim
    1.29
     you
    1.29
    "../
    1.27
    Activations Density 0.145%

    No Known Activations