© 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. 10-GEMMASCOPE-RES-131K
    7. 127865
    Prev
    Next
    INDEX
    Explanations

    resource definitions and requests

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

    The neuron is looking for occurrences of the word “resource” (e.g. in resource names or resource definitions).

    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
    .”
    -1.72
    硨
    -1.57
     immédiatement
    -1.57
    y
    -1.53
     erros
    -1.52
     bret
    -1.49
     یا
    -1.47
    全都
    -1.47
    蹀
    -1.46
     teater
    -1.44
    POSITIVE LOGITS
     these
    1.84
    <bos>
    1.82
     That
    1.77
     pueden
    1.64
    醗
    1.62
     Additionally
    1.59
     podem
    1.58
    噫
    1.57
     citado
    1.56
    argp
    1.56
    Activations Density 0.015%

    No Known Activations