© 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. 22-GEMMASCOPE-RES-131K
    7. 129332
    Prev
    Next
    INDEX
    Explanations

    The neuron responds specifically to the word “utilized.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    prior art or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     more
    -1.71
     three
    -1.59
     only
    -1.58
     on
    -1.55
     for
    -1.54
     by
    -1.52
     four
    -1.46
     with
    -1.45
     first
    -1.45
     over
    -1.44
    POSITIVE LOGITS
     olabilir
    1.46
    perhaps
    1.28
    beled
    1.27
     DIFFERENT
    1.24
    esomeness
    1.23
    amazing
    1.22
    probably
    1.21
    umph
    1.21
     AMAZING
    1.21
    ghted
    1.19
    Activations Density 0.000%

    No Known Activations