© 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. 124078
    Prev
    Next
    INDEX
    Explanations

    involved in

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

    The neuron detects mentions of entities being involved or participating in something.

    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
     if
    -2.53
     for
    -2.47
     in
    -2.22
     also
    -2.17
     on
    -2.14
     after
    -2.11
     or
    -2.08
     as
    -1.98
     only
    -1.84
     with
    -1.80
    POSITIVE LOGITS
    s
    1.68
    OUTUBE
    1.68
    actéristi
    1.66
    焢
    1.64
    ケモン
    1.64
    嫆
    1.63
    kệ
    1.60
    尨
    1.59
    簠
    1.56
    miede
    1.54
    Activations Density 0.018%

    No Known Activations