© 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. 49637
    Prev
    Next
    INDEX
    Explanations

    Brazil and variations

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

    The neuron activates on any token containing the prefix “bra” (e.g. “Braz‐” in Brazil, Brazoria, Brasch, “Brazzers,” etc.).

    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
     drier
    -0.78
    Viernes
    -0.74
    edenken
    -0.73
    Chalk
    -0.73
     Boch
    -0.71
    buen
    -0.71
    ImageBackground
    -0.70
     utter
    -0.70
     Oud
    -0.69
     pessoal
    -0.69
    POSITIVE LOGITS
    alete
    0.85
     Nut
    0.74
     Mitteln
    0.72
     卡
    0.71
     Bras
    0.71
    riad
    0.71
     Ms
    0.71
     lê
    0.68
    كن
    0.68
     âm
    0.67
    Activations Density 0.039%

    No Known Activations