© 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. 10-GEMMASCOPE-RES-131K
    7. 100696
    Prev
    Next
    INDEX
    Explanations

    Venezuela and Venezuelan

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

    The main thing this neuron does is detect mentions of “Venezuela” (and closely related forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    很容易
    -2.94
    }
    -2.77
    l
    -2.72
    有很多
    -2.61
    u
    -2.56
     corretto
    -2.50
    at
    -2.45
    廰
    -2.45
     mosso
    -2.41
     aspetta
    -2.38
    POSITIVE LOGITS
    仨
    2.14
    ↵↵
    2.08
    老爷
    1.97
    点点头
    1.91
    ↵
    1.90
     
    1.90
    想了想
    1.88
    plains
    1.84
    当即
    1.84
    СЕ
    1.82
    Activations Density 0.001%

    No Known Activations