© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15272
    Prev
    Next
    INDEX
    Explanations

    topics and questions

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

    This neuron detects the byline and metadata lines in a news article (publication names, author or desk credits, datelines, etc.).

    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
     altre
    -1.00
     altri
    -0.96
    关于
    -0.95
    лении
    -0.94
    toPromise
    -0.91
    關於
    -0.90
    湘
    -0.89
    SKA
    -0.88
    其他
    -0.87
     lakhs
    -0.85
    POSITIVE LOGITS
     aislada
    1.08
     fijar
    1.01
     Джа
    0.97
     csapat
    0.96
     teams
    0.96
    يام
    0.95
     mejorado
    0.94
     desnuda
    0.94
    挾
    0.93
    ͽ
    0.93
    Activations Density 0.001%

    No Known Activations