© 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. 22-GEMMASCOPE-RES-131K
    7. 98545
    Prev
    Next
    INDEX
    Explanations

    local leaders and groups

    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
     when
    -1.61
     or
    -1.57
     in
    -1.56
     after
    -1.32
     what
    -1.32
     for
    -1.30
     because
    -1.29
     this
    -1.27
     Does
    -1.27
     has
    -1.25
    POSITIVE LOGITS
     nombreux
    1.30
     members
    1.27
     representatives
    1.21
     decenas
    1.20
    chaussure
    1.15
     peculi
    1.13
    "}";
    1.13
     applau
    1.11
     predominantly
    1.10
     anciens
    1.10
    Activations Density 0.028%

    No Known Activations