© 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. 94030
    Prev
    Next
    INDEX
    Explanations

    musical market

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

    The neuron strongly activates on ordinary prose words (in both English and Spanish) and remains inactive on code snippets, markup, or punctuation.

    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
     disfrutando
    -1.13
     jedenfalls
    -1.08
    :-)
    -1.04
     pakai
    -1.01
     japonica
    -0.98
    няли
    -0.96
     memanfaatkan
    -0.94
     היתה
    -0.93
    =>'
    -0.92
    sólo
    -0.92
    POSITIVE LOGITS
    给予
    0.97
     данный
    0.95
     pertenec
    0.89
     expon
    0.88
     destul
    0.85
     anteriormente
    0.85
    학
    0.85
     하
    0.84
    的发展
    0.84
     incul
    0.84
    Activations Density 0.011%

    No Known Activations