© 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. 38743
    Prev
    Next
    INDEX
    Explanations

    plural forms

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

    The neuron fires specifically on the token “plural,” i.e. when the text is marking or labeling a plural form.

    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
    ↵↵
    -4.66
    \
    -4.41
    *
    -3.33
    ?
    -3.22
    ”.
    -2.92
    ]
    -2.89
    '
    -2.73
    в
    -2.72
    (
    -2.67
    “
    -2.67
    POSITIVE LOGITS
    鐿
    3.69
    ጺ
    3.22
    𓋼
    2.95
    鶺
    2.88
    cazione
    2.75
    　　*
    2.73
    Odpovědět
    2.70
    Ꮏ
    2.69
    禩
    2.63
    ссор
    2.58
    Activations Density 0.011%

    No Known Activations