© 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. 74583
    Prev
    Next
    INDEX
    Explanations

    tentative wording and provisional statements

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

    The neuron activates whenever it encounters the word “tentative” (or its derivatives like “tentatively”), signaling provisional or uncertain statements.

    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
     blessé
    -2.56
    rd
    -2.45
    ⠀⠀⠀⠀
    -2.41
    ppsala
    -2.41
     Перейти
    -2.39
     \'
    -2.25
     escrita
    -2.20
    ⠀
    -2.20
     Añade
    -2.16
    对于
    -2.14
    POSITIVE LOGITS
    ﾋ
    2.86
    の人生
    2.13
     världen
    2.09
    jestel
    2.06
     required
    2.03
    ストック
    2.02
    一共
    2.00
    )…
    1.98
    他才
    1.97
    ﾍ
    1.95
    Activations Density 0.004%

    No Known Activations