© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100923
    Prev
    Next
    INDEX
    Explanations

    auditing supervision policies

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

    formal business, technical, and administrative documents or terminology.

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

    The neuron flags formal audit‐and‐standards terminology, especially words describing audit documentation and procedural steps (e.g. “documentation,” “planning,” “supervision,” “recording,” “evidence”).

    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
     النبات
    -1.41
     catholique
    -1.38
     '\''
    -1.23
     блюдо
    -1.22
     τοῦ
    -1.21
    "}";
    -1.16
    ++);
    -1.15
     to
    -1.12
     nessa
    -1.11
     ویتامین
    -1.11
    POSITIVE LOGITS
     how
    1.46
     различни
    1.34
     different
    1.31
     peuvent
    1.26
    ünkü
    1.23
    kapat
    1.23
     semarang
    1.23
     your
    1.23
     related
    1.21
     можуть
    1.21
    Activations Density 0.097%

    No Known Activations