© 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. 90619
    Prev
    Next
    INDEX
    Explanations

    "Q:" followed by technical description

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

    The neuron strongly fires on Java source‐file headers—specifically package and import declaration tokens.

    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
    НИК
    -0.89
    çuk
    -0.81
    ДУ
    -0.78
     pomi
    -0.78
     Resolución
    -0.77
    Brooklyn
    -0.77
    тным
    -0.77
    海の
    -0.77
     PATENT
    -0.76
    ТУ
    -0.76
    POSITIVE LOGITS
     Souver
    0.77
     sover
    0.76
     خلف
    0.76
     cães
    0.75
     Brugge
    0.73
    nexo
    0.71
     Bruch
    0.69
    thru
    0.69
     Fernand
    0.69
     Iberian
    0.69
    Activations Density 0.005%

    No Known Activations