© 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. 85248
    Prev
    Next
    INDEX
    Explanations

    invoking model methods

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

    The neuron fires on PHP object method names (the identifiers that follow the “->” operator, e.g. get, getModel, where, row).

    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
     because
    -1.60
     should
    -1.59
     first
    -1.57
    大多
    -1.52
     отличаются
    -1.45
     still
    -1.44
    훗
    -1.43
    コミュニティ
    -1.42
    quale
    -1.42
    多く
    -1.42
    POSITIVE LOGITS
    踅
    1.73
    fatalError
    1.63
    )();
    1.60
     dezelve
    1.56
     bebê
    1.52
    ↵↵
    1.50
     uska
    1.48
     ſte
    1.48
     kog
    1.47
     œufs
    1.46
    Activations Density 0.001%

    No Known Activations