© 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. 72393
    Prev
    Next
    INDEX
    Explanations

    medium heat

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

    The neuron activates on cooking‐recipe language—especially measurements, cookware terms, and cooking instructions.

    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
     it
    -1.75
    荦
    -1.73
    "},
    -1.70
    Ꮉ
    -1.66
    ਃ
    -1.64
    '),
    -1.61
    👨
    -1.58
    👩
    -1.55
    ㅇ
    -1.52
    **/
    -1.48
    POSITIVE LOGITS
     or
    2.02
    The
    1.75
    This
    1.72
    _
    1.49
    If
    1.44
    篩
    1.42
    Groet
    1.38
    You
    1.34
    These
    1.34
     if
    1.33
    Activations Density 0.004%

    No Known Activations