© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99947
    Prev
    Next
    INDEX
    Explanations

    as followed by word

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

    This neuron activates on occurrences of the word “as.”

    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
    鹛
    -2.11
    kommt
    -2.03
    Törté
    -1.99
    ꦢ
    -1.98
    菝
    -1.90
    齜
    -1.85
    茕
    -1.84
    柺
    -1.77
     poroz
    -1.75
    ſſen
    -1.73
    POSITIVE LOGITS
    '
    2.73
     a
    2.48
     an
    2.13
    "
    1.98
    ?
    1.98
    s
    1.79
     many
    1.72
    ....
    1.70
     Traditionally
    1.66
    However
    1.66
    Activations Density 0.056%

    No Known Activations