© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87055
    Prev
    Next
    INDEX
    Explanations

    sports team and player names

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

    The main thing this neuron does is find numeric tokens (i.e. numbers and digit sequences).

    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
    Queen
    -0.77
     pageNumber
    -0.73
    Club
    -0.73
    camb
    -0.72
    ignants
    -0.71
    spikes
    -0.71
     página
    -0.70
    хня
    -0.69
     Einführung
    -0.69
    潜在
    -0.69
    POSITIVE LOGITS
    ylar
    0.84
    ILER
    0.79
     forward
    0.76
    RSVP
    0.75
    illons
    0.74
     bekannte
    0.73
     サム
    0.73
     Goals
    0.72
    forward
    0.71
     kot
    0.71
    Activations Density 0.012%

    No Known Activations