© 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. 34-GEMMASCOPE-RES-131K
    7. 103408
    Prev
    Next
    INDEX
    Explanations

    either version

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

    The neuron identifies words and phrases typical of open‐source license boilerplate (e.g. “free,” “you,” “either,” “Foundation,” “Copyright,” “Version”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Reilly
    -0.82
    alse
    -0.79
    exo
    -0.75
    Assoc
    -0.73
    gines
    -0.73
     imme
    -0.73
    iny
    -0.72
     tcp
    -0.70
     corresponde
    -0.69
    preis
    -0.68
    POSITIVE LOGITS
     climbed
    0.70
     розвитку
    0.69
    펴
    0.65
    taps
    0.63
     Innenstadt
    0.60
     mainly
    0.60
    ♗
    0.60
    鈿
    0.60
     solely
    0.60
    열
    0.59
    Activations Density 0.082%

    No Known Activations