© 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. 119898
    Prev
    Next
    INDEX
    Explanations

    proper noun phrases and technical terms

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

    JSON or structured data formatting, particularly whitespace and delimiters like quotes, colons, and braces.

    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
    ּוֹ
    -2.44
    ֶּ
    -1.87
     of
    -1.73
     verminder
    -1.61
     onderdelen
    -1.58
     vó
    -1.58
    וּ
    -1.58
    ᾽
    -1.57
     illustratie
    -1.55
    ַּ
    -1.55
    POSITIVE LOGITS
     katholischen
    2.17
     kathol
    1.93
     christlichen
    1.90
     religieuses
    1.76
     children
    1.76
     mismas
    1.73
    因為
    1.72
    เพราะ
    1.70
     württemberg
    1.70
     propuestas
    1.67
    Activations Density 0.005%

    No Known Activations