© 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. 67260
    Prev
    Next
    INDEX
    Explanations

    a variety of

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

    the neuron detects quantifier phrases expressing a range of items or categories (e.g. “a variety of,” “diverse set of”).

    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
    ܇
    -1.55
    .../
    -1.44
     یا
    -1.38
    Hanya
    -1.38
    lihood
    -1.37
    istica
    -1.36
    ／
    -1.36
    .'/
    -1.36
    ageable
    -1.35
     kilometre
    -1.35
    POSITIVE LOGITS
     of
    2.11
     its
    1.87
     different
    1.71
     our
    1.69
     We
    1.66
    </em>
    1.62
    idjan
    1.45
     both
    1.43
     Our
    1.42
     diverse
    1.41
    Activations Density 0.105%

    No Known Activations