© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    temper, tempered, temperate

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

    This neuron activates on words containing the substring “temper” (e.g. temper, tempered, distemper).

    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
    轳
    -2.72
    s
    -2.70
    "
    -2.69
    '
    -2.52
    锨
    -2.48
    錞
    -2.44
     berech
    -2.33
    ࿆
    -2.30
    縂
    -2.28
    盌
    -2.27
    POSITIVE LOGITS
    ),
    3.08
    </h2>
    2.95
    Sekarang
    2.67
    Setelah
    2.67
    Sebelum
    2.47
    麪
    2.45
    what
    2.36
    纜
    2.34
    熒
    2.27
    呓
    2.27
    Activations Density 0.004%

    No Known Activations