© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113694
    Prev
    Next
    INDEX
    Explanations

    code structure and identifiers

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

    numeric digits, especially in version numbers, dates, and technical identifiers in code.

    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
    issez
    -1.55
    
    -1.53
     حتی
    -1.46
     jego
    -1.45
    czego
    -1.43
    chengladbach
    -1.38
     wektor
    -1.38
     nawet
    -1.38
     acheter
    -1.34
     desplaz
    -1.34
    POSITIVE LOGITS
     these
    2.11
     this
    2.06
     was
    1.87
     will
    1.86
     an
    1.69
    Some
    1.63
    最後に
    1.59
    These
    1.55
     definitively
    1.54
     are
    1.49
    Activations Density 0.001%

    No Known Activations