© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86845
    Prev
    Next
    INDEX
    Explanations

    trans, decimals, postgres

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

    The neuron strongly fires on tokens ending in “s” (i.e. typical English plural or third‐person-singular forms).

    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
    i
    -3.28
    e
    -3.23
     algunos
    -2.77
    遢
    -2.69
    ed
    -2.58
    い
    -2.53
    u
    -2.48
    蹌
    -2.48
    焄
    -2.42
     wich
    -2.34
    POSITIVE LOGITS
    臵
    3.13
    蠖
    3.09
    lossians
    2.89
    ༵
    2.73
    F
    2.72
    鲮
    2.66
    H
    2.63
    廕
    2.63
     américa
    2.61
    戆
    2.61
    Activations Density 0.002%

    No Known Activations