© 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. 68630
    Prev
    Next
    INDEX
    Explanations

    types of companies or products

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

    The neuron activates most strongly on names of classical music works and ensembles (e.g. “Tchaikovsky Concerto” and “Vancouver Symphony Orchestra”).

    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
    set
    -1.10
    をします
    -1.09
    load
    -1.05
    を行い
    -0.97
     propri
    -0.97
    qiang
    -0.96
    FECHA
    -0.96
    を行います
    -0.96
    ਲ਼
    -0.95
    le
    -0.94
    POSITIVE LOGITS
     with
    1.26
    mariage
    1.09
     kré
    1.07
     ajedrez
    1.02
    lifford
    1.02
     行っ
    0.99
     from
    0.99
     béisbol
    0.95
    และ
    0.94
     الأخيرة
    0.93
    Activations Density 0.023%

    No Known Activations