© 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. 45427
    Prev
    Next
    INDEX
    Explanations

    San Francisco 49ers

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

    The neuron detects mentions of the “49ers” (i.e. the token sequence referencing the San Francisco 49ers).

    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
    Raja
    -0.78
     scrubs
    -0.74
    ställning
    -0.73
    fehlungen
    -0.73
    Carrito
    -0.71
    组合
    -0.69
     smears
    -0.69
     çerçe
    -0.68
     treads
    -0.68
    ╗
    -0.68
    POSITIVE LOGITS
    lications
    0.90
     autobus
    0.88
    StylePriority
    0.84
     San
    0.82
    INARY
    0.79
     moj
    0.77
     القد
    0.76
    藉
    0.74
     OPER
    0.71
     superficial
    0.71
    Activations Density 0.047%

    No Known Activations