© 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. 11567
    Prev
    Next
    INDEX
    Explanations

    agreement or acceptance

    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
     they
    -1.70
    uſe
    -1.50
     about
    -1.49
     \
    -1.49
    niť
    -1.45
    schwe
    -1.43
    \
    -1.41
     Acht
    -1.40
     Sitten
    -1.40
     tenía
    -1.39
    POSITIVE LOGITS
    rogates
    1.48
     dispozici
    1.44
    ového
    1.42
     hoher
    1.40
     行っ
    1.39
     tomadas
    1.36
     suministros
    1.34
     that
    1.33
     manguera
    1.33
     -
    1.31
    Activations Density 0.011%

    No Known Activations