© 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. 86725
    Prev
    Next
    INDEX
    Explanations

    field distribution systems

    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
    ↵↵
    -1.34
     navnet
    -1.27
     guapos
    -1.25
     trattamento
    -1.23
     botines
    -1.21
    leyici
    -1.20
     peccato
    -1.20
     mejoras
    -1.17
    AMIENTO
    -1.13
     остался
    -1.09
    POSITIVE LOGITS
    -"
    1.44
     ?"
    1.32
     Again
    1.31
     counterparts
    1.30
     to
    1.30
    .."
    1.28
     sebagainya
    1.26
    --"
    1.25
     ."
    1.25
    '"
    1.25
    Activations Density 0.054%

    No Known Activations