© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112111
    Prev
    Next
    INDEX
    Explanations

    list formatting and coding

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

    technical or specialized terms, particularly compound words or abbreviations in formal/technical contexts.

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

    The neuron fires strongly on content‐bearing technical or domain-specific nouns (jargon and specialized terms) rather than on common function words.

    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
     correctement
    -1.77
     geene
    -1.67
    probably
    -1.67
     eksklu
    -1.66
     réellement
    -1.65
    
    -1.63
    ඞ
    -1.55
    ఝ
    -1.55
     miniaturka
    -1.55
    zzet
    -1.54
    POSITIVE LOGITS
     with
    2.31
     on
    2.28
     being
    2.22
     would
    2.11
     new
    2.03
     in
    2.02
     will
    1.97
     as
    1.95
     Being
    1.82
     =
    1.81
    Activations Density 0.184%

    No Known Activations