© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43614
    Prev
    Next
    INDEX
    Explanations

    feeling plus descriptor

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

    The neuron strongly activates on occurrences of the word “feeling.”

    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
     humeur
    -3.23
    s
    -3.17
    风
    -2.89
    \
    -2.83
    e
    -2.80
     capelli
    -2.73
    ቼ
    -2.70
    嵛
    -2.70
    𝑚
    -2.67
     odeur
    -2.63
    POSITIVE LOGITS
    the
    2.91
    弍
    2.72
     umfang
    2.72
    姈
    2.70
     Betracht
    2.70
     of
    2.63
    眼下
    2.58
    を変える
    2.48
     hierzu
    2.42
    <bos>
    2.41
    Activations Density 0.004%

    No Known Activations