© 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. 34-GEMMASCOPE-RES-131K
    7. 117508
    Prev
    Next
    INDEX
    Explanations

    PLoS, Instagram, Vine, WWE

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

    The neuron primarily detects numeric tokens (scores, times, dates, or other numbers) in sports and match contexts.

    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
    enschappelijke
    -0.74
    렐
    -0.72
     Frontiers
    -0.69
    Мо
    -0.68
    頌
    -0.67
    Keith
    -0.66
    FRONT
    -0.65
     Emmer
    -0.64
    Frontend
    -0.64
    Lime
    -0.64
    POSITIVE LOGITS
     PLoS
    0.95
     Vine
    0.85
     PLO
    0.85
    PLOS
    0.82
     PLOS
    0.80
     Plo
    0.77
    grafo
    0.75
    instagram
    0.75
    plo
    0.74
    utete
    0.74
    Activations Density 0.049%

    No Known Activations