© 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. 12560
    Prev
    Next
    INDEX
    Explanations

    cutting materials

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the verb “cut” (including its inflected forms).

    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
    {
    -2.77
    .
    -2.27
    after
    -1.77
     Since
    -1.67
    e
    -1.66
     on
    -1.61
    ar
    -1.54
     Aside
    -1.52
    gitte
    -1.48
    roslav
    -1.48
    POSITIVE LOGITS
    诳
    2.09
     $\&$
    2.08
     acoged
    2.05
    螣
    1.95
    开车
    1.91
     sabias
    1.91
     cut
    1.86
    驺
    1.86
     acogedor
    1.85
     meestal
    1.84
    Activations Density 0.090%

    No Known Activations