© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103995
    Prev
    Next
    INDEX
    Explanations

    code blocks and commands

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

    numeric list item indicators, particularly numbers followed by periods or colons in structured documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects numbered list markers or section headings (e.g. standalone digits followed by punctuation) in a document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     detayl
    -1.48
    atecas
    -1.41
     primeiras
    -1.35
    垕
    -1.35
    </h4>
    -1.33
    /',
    -1.32
     moeten
    -1.30
    /";
    -1.30
    langsung
    -1.25
    ニーズ
    -1.25
    POSITIVE LOGITS
    </i>
    1.52
     SimpleName
    1.39
     "
    1.35
     they
    1.34
     درمانی
    1.26
     recommend
    1.24
     rezept
    1.24
     mármol
    1.23
     его
    1.22
    薷
    1.22
    Activations Density 0.055%

    No Known Activations