© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9948
    Prev
    Next
    INDEX
    Explanations

    bifurcation

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

    The neuron reliably fires on occurrences of the term “bifurcation” (including its subword segments) in technical or scientific contexts.

    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
     prioriti
    -2.58
    螻
    -2.38
    our
    -2.22
    暃
    -2.20
    嗩
    -2.19
    หรือ
    -2.17
    勉强
    -2.16
    ㅁ
    -2.13
    侥
    -2.13
    ୮
    -2.11
    POSITIVE LOGITS
    ’
    2.94
    u
    2.70
    s
    2.47
    After
    2.17
     BOTH
    2.11
    Another
    2.09
     儿童
    2.08
    The
    2.06
     После
    2.03
    有不少
    2.03
    Activations Density 0.006%

    No Known Activations