© 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. 130777
    Prev
    Next
    INDEX
    Explanations

    array analysis / gene expression

    np_acts-logits-general · gemini-2.5-flash-lite

    technology-related terms like programming languages, software platforms, and electronic devices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     by
    -1.90
     there
    -1.77
     about
    -1.77
     through
    -1.73
     something
    -1.70
     In
    -1.65
     it
    -1.63
     within
    -1.59
     this
    -1.59
     some
    -1.56
    POSITIVE LOGITS
     of
    1.57
     její
    1.45
    ulieren
    1.44
    bitkan
    1.42
    REGON
    1.41
    JDK
    1.39
     CONTRIBUTORS
    1.37
    πομπές
    1.35
    kennen
    1.35
     où
    1.35
    Activations Density 0.085%

    No Known Activations