© 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. 118765
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    structured data format syntax, particularly JSON, XML, and programming language code with punctuation like colons, brackets, and quotes.

    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
     by
    -1.66
    ytale
    -1.57
    neous
    -1.57
     («
    -1.53
    thodoxy
    -1.46
    )…
    -1.38
    NTIS
    -1.37
    preneurs
    -1.34
     «
    -1.32
     उनके
    -1.31
    POSITIVE LOGITS
     time
    1.52
     adatta
    1.48
     máme
    1.48
     meravigli
    1.45
     mojej
    1.41
     musíte
    1.37
     erhi
    1.34
    8
    1.34
     mohou
    1.30
     Empieza
    1.30
    Activations Density 0.086%

    No Known Activations