© 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. 57439
    Prev
    Next
    INDEX
    Explanations

    code identifiers and definitions

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

    The neuron spikes on title‐style or identifier tokens—i.e. words in TitleCase or ALL-Caps that serve as section headings, class/function names, or other code identifiers.

    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
     and
    -1.70
     but
    -1.57
    !*\
    -1.55
     memiliki
    -1.37
    άνει
    -1.33
    =");
    -1.32
    برة
    -1.30
     sekitar
    -1.28
     "}";
    -1.27
    veloper
    -1.25
    POSITIVE LOGITS
    _
    1.66
     außerdem
    1.45
     zudem
    1.42
     baratas
    1.26
     réalisées
    1.24
     ibang
    1.21
     armé
    1.21
     chileno
    1.19
     anderer
    1.16
    除此之外
    1.16
    Activations Density 0.197%

    No Known Activations