© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    Bis- prefix words

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

    The neuron activates on occurrences of the letter sequence “bis” as a chemical‐naming prefix.

    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
    沨
    -3.27
    夘
    -3.02
    狴
    -3.02
    旰
    -2.91
    ︲
    -2.89
    脔
    -2.88
    に乗って
    -2.84
    婠
    -2.84
    撄
    -2.81
    艄
    -2.77
    POSITIVE LOGITS
    e
    3.88
     When
    3.36
    During
    3.33
    When
    3.31
    s
    3.20
     Когда
    3.06
    After
    2.95
    How
    2.94
    What
    2.94
    d
    2.86
    Activations Density 0.022%

    No Known Activations