© 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. 34-GEMMASCOPE-RES-131K
    7. 108593
    Prev
    Next
    INDEX
    Explanations

    film and production roles

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

    The neuron fires strongly on capitalized proper nouns—names of people, companies, and other named entities.

    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
    Dış
    -0.75
     Lebensmittel
    -0.72
     Elapsed
    -0.71
    ないです
    -0.70
     solicitudes
    -0.69
     swallowed
    -0.69
     infecciones
    -0.68
     profeta
    -0.66
     conex
    -0.66
    Relations
    -0.66
    POSITIVE LOGITS
     élevées
    0.79
    ikum
    0.78
    isco
    0.78
    =='
    0.77
     financiers
    0.77
    cellation
    0.77
    Thursday
    0.75
     produire
    0.75
    ⛵
    0.75
    ḱ
    0.75
    Activations Density 0.031%

    No Known Activations