© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102236
    Prev
    Next
    INDEX
    Explanations

    her, she, his, him

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

    The neuron primarily activates on occurrences of the words “HER,” “His,” or “her,” i.e., possessive pronouns (often capitalized) referring to gender.

    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
     of
    -1.66
     ');
    -1.55
    overline
    -1.48
    我们的
    -1.48
     forState
    -1.47
     innych
    -1.44
    assertEqual
    -1.43
    olução
    -1.43
    され
    -1.41
    olver
    -1.41
    POSITIVE LOGITS
     and
    1.70
     ‘‘
    1.58
    能在
    1.48
    ’,
    1.41
     but
    1.40
     amplia
    1.39
     türlü
    1.38
     simplement
    1.33
    simply
    1.31
     ayudó
    1.30
    Activations Density 0.032%

    No Known Activations