© 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. 101604
    Prev
    Next
    INDEX
    Explanations

    separate or distinct entities

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

    The neuron is strongly activated by words that denote separation or distinction (e.g. “separate,” “distinct”).

    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
    .
    -1.88
     for
    -1.38
     is
    -1.38
     his
    -1.23
     on
    -1.21
     see
    -1.17
     the
    -1.16
     where
    -1.16
    :
    -1.14
    ll
    -1.11
    POSITIVE LOGITS
    uberge
    1.74
     навіть
    1.70
    anmar
    1.52
     アルバム
    1.52
     integrados
    1.51
    そして
    1.50
    然后
    1.48
    并且
    1.47
    Médaille
    1.46
     jį
    1.45
    Activations Density 0.050%

    No Known Activations