© 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. 22-GEMMASCOPE-RES-131K
    7. 67433
    Prev
    Next
    INDEX
    Explanations

    fishing and related activities

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

    The neuron fires strongly on occurrences of “fishing” and related fish-activity terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     trámites
    -2.02
     that
    -1.93
    梣
    -1.92
    氽
    -1.91
    ！！！！！
    -1.80
    ꯲
    -1.80
    ᱾
    -1.78
    entlichen
    -1.73
     gratuito
    -1.73
    
    -1.73
    POSITIVE LOGITS
    -
    2.08
     That
    1.83
     When
    1.73
    но
    1.70
     在
    1.66
     gän
    1.62
     angefü
    1.62
     Einfluß
    1.61
     To
    1.60
    ри
    1.59
    Activations Density 0.005%

    No Known Activations