© 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. 40453
    Prev
    Next
    INDEX
    Explanations

    UI element initialization and properties

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

    The neuron fires on code identifiers and member names—especially PascalCase method, class, and control names—in source 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
     with
    -1.66
    ,
    -1.55
    ha
    -1.37
    进一步
    -1.33
    ig
    -1.25
     also
    -1.25
     mereka
    -1.24
    wa
    -1.23
    ol
    -1.20
     and
    -1.17
    POSITIVE LOGITS
     this
    1.73
     maravill
    1.46
    utusan
    1.42
     essayé
    1.37
     puentes
    1.34
     тобой
    1.32
    ┖
    1.32
    crire
    1.32
    epik
    1.31
    蚡
    1.31
    Activations Density 0.019%

    No Known Activations