© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100397
    Prev
    Next
    INDEX
    Explanations

    information transfer or communication

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

    nouns that represent data, information, or resources being communicated, transferred, or contained.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical or formal nouns, particularly in specialized contexts like patents, scientific papers, and technical documentation.

    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
     will
    -2.47
     it
    -1.80
     now
    -1.78
     this
    -1.63
     if
    -1.62
     can
    -1.61
    this
    -1.59
    >
    -1.55
    
    -1.53
    /*
    -1.52
    POSITIVE LOGITS
     própri
    1.63
     signifikan
    1.62
     meur
    1.59
     fermer
    1.58
     alerg
    1.56
    ÑOS
    1.55
     chanteur
    1.55
     fidé
    1.55
    насе
    1.52
     malade
    1.51
    Activations Density 1.059%

    No Known Activations