© 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. 34-GEMMASCOPE-RES-131K
    7. 81291
    Prev
    Next
    INDEX
    Explanations

    quoted strings and code structures

    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_34/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
     in
    -1.27
     for
    -1.25
    For
    -1.20
     when
    -1.12
     at
    -1.08
    At
    -1.08
     that
    -1.07
     if
    -1.05
     still
    -1.05
     give
    -1.04
    POSITIVE LOGITS
    quite
    1.35
    unfortunately
    1.31
    perfectly
    1.27
    normally
    1.23
    combined
    1.20
    primarily
    1.18
    launched
    1.17
    automatically
    1.16
     benevol
    1.15
    definitely
    1.14
    Activations Density 0.050%

    No Known Activations