© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47646
    Prev
    Next
    INDEX
    Explanations

    Bahamas and Nassau

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

    The neuron activates on four-digit numerical tokens (e.g. “1032,” “2096,” “1412”).

    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
     boroughs
    -0.88
    以上就是
    -0.80
     Tunisian
    -0.76
    сказа
    -0.75
     significato
    -0.75
    網頁
    -0.74
    جرة
    -0.74
    Tess
    -0.72
     Lilith
    -0.72
     might
    -0.70
    POSITIVE LOGITS
     Bahamas
    2.03
     Nassau
    1.97
     Baha
    1.68
    Nassau
    1.63
    Baha
    1.62
    baha
    1.47
     Ba
    1.41
     baha
    1.35
    Ba
    1.24
    🇧
    1.09
    Activations Density 0.006%

    No Known Activations