© 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. 65959
    Prev
    Next
    INDEX
    Explanations

    Buffalo

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

    The neuron primarily activates on occurrences of the word “Buffalo” (the place name).

    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
    1
    -3.03
    t
    -2.73
    不错
    -2.56
    事實
    -2.55
    同じ
    -2.48
    of
    -2.48
    S
    -2.39
    袿
    -2.38
     неболь
    -2.34
    他們的
    -2.34
    POSITIVE LOGITS
    媗
    2.55
    <bos>
    2.45
    s
    2.38
    荜
    2.38
    也被
    2.31
    ścić
    2.30
    жаться
    2.30
    cinoma
    2.30
     bleek
    2.27
    िया
    2.23
    Activations Density 0.002%

    No Known Activations