© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47811
    Prev
    Next
    INDEX
    Explanations

    sports governing bodies and events

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

    The neuron strongly activates on numeric and related tokens (digits, dates, dashes, punctuation marks), i.e. elements encoding numbers or numerical information.

    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
    冬天
    -0.74
     ovos
    -0.71
    GenerationType
    -0.71
     Freshman
    -0.69
     Ekiti
    -0.69
     generar
    -0.68
     وانت
    -0.68
    假期
    -0.68
    ковский
    -0.68
     चुन
    -0.68
    POSITIVE LOGITS
     FIFA
    2.39
    FIFA
    1.99
     UEFA
    1.95
     NCAA
    1.70
    UEFA
    1.59
     FIA
    1.52
     NHL
    1.48
     FIBA
    1.48
     governing
    1.47
     IOC
    1.47
    Activations Density 0.076%

    No Known Activations