© 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. 101809
    Prev
    Next
    INDEX
    Explanations

    programming concepts and techniques

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

    technical programming and software-related terms in code documentation and questions.

    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
    
    -1.48
     intricate
    -1.36
     poner
    -1.35
     gives
    -1.34
     our
    -1.32
     some
    -1.30
    intl
    -1.30
    %">
    -1.29
     >
    -1.27
     haphazard
    -1.27
    POSITIVE LOGITS
     sweter
    1.73
     Consejos
    1.67
     bocetos
    1.61
     utafiti
    1.59
     Ráp
    1.55
    yectos
    1.53
     felicitación
    1.49
     puntuación
    1.46
     privacidad
    1.44
     vrouwen
    1.41
    Activations Density 0.048%

    No Known Activations