© 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. 8140
    Prev
    Next
    INDEX
    Explanations

    Calla Gold, Heidelberg Cement, TEC Award, McGill Pain

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

    The neuron fires on individual tokens that contain numeric characters (e.g. “TEC 120,” “Calla 97,” “Mori 91,” etc.).

    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
    \
    -2.91
    蟶
    -2.83
     mostr
    -2.78
     så
    -2.75
    鶺
    -2.70
    媜
    -2.56
     personnelles
    -2.56
    転車
    -2.48
    遢
    -2.45
    姈
    -2.44
    POSITIVE LOGITS
    ’
    3.89
     selben
    3.14
     But
    3.11
     It
    3.05
    e
    3.00
     “
    2.78
     has
    2.48
     and
    2.44
     All
    2.34
     Económica
    2.34
    Activations Density 0.016%

    No Known Activations