© 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. 103974
    Prev
    Next
    INDEX
    Explanations

    individual items and specific conditions

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

    The neuron specifically detects the word “individual.”

    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
    鍇
    -1.75
     Хор
    -1.50
     as
    -1.49
     superbly
    -1.48
     or
    -1.44
     deliciosa
    -1.41
     providing
    -1.41
     maleta
    -1.40
     EVERY
    -1.40
     JUST
    -1.40
    POSITIVE LOGITS
     ,‬
    1.91
     bottes
    1.88
    ['_
    1.84
    rops
    1.80
    6
    1.69
    pressor
    1.68
    which
    1.67
    t
    1.67
    睃
    1.63
    hiker
    1.59
    Activations Density 0.024%

    No Known Activations