© 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. 114
    Prev
    Next
    INDEX
    Explanations

    data parameters

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

    the word "data" followed by a colon or equals sign in code contexts, particularly in API calls and data assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     citroen
    -1.57
    躥
    -1.27
     inox
    -1.24
     rapporte
    -1.22
     Wants
    -1.21
    ՚
    -1.20
    त्र
    -1.20
     occuper
    -1.20
     knop
    -1.18
    ܸ
    -1.18
    POSITIVE LOGITS
     for
    1.84
     When
    1.61
     with
    1.45
    ;
    1.30
     and
    1.27
     kesempatan
    1.27
     That
    1.25
     should
    1.24
    When
    1.22
    
    1.20
    Activations Density 0.020%

    No Known Activations