© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86096
    Prev
    Next
    INDEX
    Explanations

    made by, of, in, from, for

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

    The neuron strongly activates on the past‐participle verb "made" (e.g. "made of," "made up of," "made by").

    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
     to
    -1.86
     but
    -1.83
    </i>
    -1.83
     a
    -1.79
     so
    -1.76
    circ
    -1.57
    餮
    -1.56
     if
    -1.50
     thier
    -1.48
    炱
    -1.45
    POSITIVE LOGITS
    鈊
    1.73
     "'");
    1.67
    茔
    1.56
     celebrated
    1.56
    脔
    1.55
    )$,
    1.54
     "";
    1.54
    GGI
    1.52
     стоковые
    1.51
     empêcher
    1.50
    Activations Density 0.037%

    No Known Activations