© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19556
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    The neuron fires on programming identifiers and API names (e.g. class, method, and constant names) in code snippets.

    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
     после
    -1.22
    }\
    -1.20
     båda
    -1.19
     monthly
    -1.15
     and
    -1.10
     conseguiu
    -1.10
     kiedy
    -1.08
    inu
    -1.07
    elon
    -1.06
     enää
    -1.06
    POSITIVE LOGITS
     that
    1.52
     to
    1.45
     such
    1.25
     volcán
    1.20
     what
    1.20
     including
    1.17
     even
    1.14
    larıyla
    1.12
     some
    1.12
     on
    1.09
    Activations Density 0.038%

    No Known Activations