© 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. 10013
    Prev
    Next
    INDEX
    Explanations

    software construction and testing

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

    the word "stub" or its variants (stubs, stubbed) in programming and technical contexts.

    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
    떳
    -3.39
    谖
    -3.36
    呖
    -2.80
    铙
    -2.67
    絝
    -2.52
    횃
    -2.47
     maniere
    -2.42
    IZACIÓN
    -2.39
    
    -2.36
    剮
    -2.34
    POSITIVE LOGITS
    <bos>
    2.45
     zarówno
    2.36
    end
    2.36
    ‘
    2.31
    ’
    2.31
    好似
    2.22
    1
    2.22
     zostały
    2.19
     lofty
    2.16
     смысле
    2.16
    Activations Density 0.003%

    No Known Activations