© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9288
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by terms

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

    The neuron is triggered by mathematical/expression tokens—operators (like “*” and “/”) and math context words (e.g. “assuming”) in algebraic formulas.

    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
    幾個
    -1.68
    選ぶ
    -1.30
    地圖
    -1.29
    フラット
    -1.25
    三個
    -1.22
     crucified
    -1.21
     einzige
    -1.17
    jenige
    -1.16
     Comunidad
    -1.16
    点此
    -1.16
    POSITIVE LOGITS
     we
    1.78
    </strong>
    1.65
    ).
    1.54
     beider
    1.45
    ’,
    1.42
    siamo
    1.41
    empio
    1.40
     zobaczyć
    1.38
    klü
    1.38
    she
    1.35
    Activations Density 0.465%

    No Known Activations