© 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. 22-GEMMASCOPE-RES-131K
    7. 338
    Prev
    Next
    INDEX
    Explanations

    anyone

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

    The neuron strongly activates on generic indefinite‐person pronouns (e.g. “anyone,” “someone”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    somewhat
    -2.39
     berbagai
    -2.36
     wonderfully
    -2.33
    俛
    -2.33
    ことも
    -2.28
     monstrous
    -2.25
    蹀
    -2.23
     delightful
    -2.23
    acterísticas
    -2.22
     somewhat
    -2.16
    POSITIVE LOGITS
     else
    3.28
    輒
    2.28
    $
    2.25
    甡
    2.13
    .
    2.13
    AutoresizingMask
    2.13
    蜮
    2.03
    '
    1.97
    jęcia
    1.94
    📖
    1.94
    Activations Density 0.031%

    No Known Activations