© 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. 85184
    Prev
    Next
    INDEX
    Explanations

    prefix punctuation and code elements

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

    The neuron fires on JavaScript lines assigning UI label strings (e.g. toolbar or heading names) to properties in a `.strings[...]` object.

    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
    There
    -1.84
    由於
    -1.80
     aient
    -1.77
    Since
    -1.73
     visant
    -1.71
    Once
    -1.67
    Taking
    -1.66
    Surprisingly
    -1.66
    根據
    -1.66
    If
    -1.64
    POSITIVE LOGITS
     is
    2.44
     also
    2.13
     a
    2.09
     was
    1.73
     now
    1.69
     not
    1.65
     it
    1.63
     to
    1.63
     never
    1.60
     largely
    1.59
    Activations Density 0.002%

    No Known Activations