© 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. 71001
    Prev
    Next
    INDEX
    Explanations

    same-sex marriage or partners

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

    The neuron responds to standalone technical or feature‐label nouns (e.g. “dial,” “tone,” “blue,” “sex,” “gene,” “trait,” “system,” “mesh”).

    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
     -
    -2.25
    “
    -2.02
     would
    -1.99
    in
    -1.98
     on
    -1.95
    .”
    -1.95
    0
    -1.94
     they
    -1.84
     or
    -1.79
    or
    -1.77
    POSITIVE LOGITS
    pady
    1.80
    ühnen
    1.77
    nargs
    1.73
    aphne
    1.72
    ˃
    1.70
    ním
    1.68
    erráneo
    1.68
     sentada
    1.66
     détru
    1.64
    🔺
    1.64
    Activations Density 0.128%

    No Known Activations