© 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. 10192
    Prev
    Next
    INDEX
    Explanations

    programming contexts and bios

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

    colons that introduce or follow labels, metadata fields, or section headers in structured text and code.

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

    This neuron responds strongly to code- and markup-specific tokens—e.g. function/module names, object property identifiers, and HTML tag names.

    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
     you
    -1.34
     your
    -1.30
     не
    -1.28
    Ꮪ
    -1.24
    pylene
    -1.24
    SaveChangesAsync
    -1.22
    而
    -1.22
     через
    -1.20
     производстве
    -1.19
     quotidienne
    -1.18
    POSITIVE LOGITS
     and
    1.71
     olvidar
    1.45
     encontr
    1.43
     how
    1.35
    殽
    1.34
     când
    1.30
     descansar
    1.28
     acudir
    1.24
     comprender
    1.21
    + 
    1.21
    Activations Density 0.003%

    No Known Activations