© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86138
    Prev
    Next
    INDEX
    Explanations

    user interface elements

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

    The neuron fires on words that label sections, features, modes, settings, or other configurable/options-style headings in the text.

    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
     using
    -1.95
     from
    -1.79
     while
    -1.78
     this
    -1.72
     despite
    -1.70
     just
    -1.65
     there
    -1.63
     it
    -1.61
     during
    -1.61
     Despite
    -1.59
    POSITIVE LOGITS
     that
    1.93
     andere
    1.84
     foton
    1.82
     flink
    1.80
     flotte
    1.76
     autres
    1.72
     nimmer
    1.72
     formel
    1.69
     ferie
    1.66
     hermé
    1.66
    Activations Density 0.262%

    No Known Activations