© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    namesake, titular, self-titled

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

    The neuron detects words referring to a work’s title (e.g. “eponymous,” “titular”).

    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
     Even
    -1.66
     bahkan
    -1.63
     only
    -1.63
     even
    -1.59
     (
    -1.59
     Fassung
    -1.55
     just
    -1.54
     ONLY
    -1.53
     Only
    -1.52
    dataloader
    -1.52
    POSITIVE LOGITS
     fatale
    1.80
    镦
    1.70
     umane
    1.60
    
    1.60
     moderne
    1.60
     intelligente
    1.59
    iffance
    1.56
     keramik
    1.55
     biss
    1.55
     trouvé
    1.51
    Activations Density 0.013%

    No Known Activations