© 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. 100126
    Prev
    Next
    INDEX
    Explanations

    grammatical relations and forms

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

    The neuron is specifically detecting occurrences of the word “grammatical.”

    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
    嫆
    -3.11
    ᯾
    -3.03
    𖧵
    -2.95
    ⛦
    -2.89
    鸶
    -2.83
     kabát
    -2.80
     bebés
    -2.78
     meleg
    -2.64
     estadía
    -2.63
    ᥬ
    -2.59
    POSITIVE LOGITS
    1
    3.56
    '
    3.16
    Of
    3.09
     намного
    2.83
    by
    2.63
     This
    2.61
    ^{\
    2.59
    0
    2.58
    2
    2.56
    可以
    2.53
    Activations Density 0.001%

    No Known Activations