© 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. 22-GEMMASCOPE-RES-131K
    7. 64933
    Prev
    Next
    INDEX
    Explanations

    multiplication and product descriptions

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

    The neuron activates on words naming or symbolizing mathematical operations (e.g. addition, multiplication, AND, OR, odot).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    斯克
    -1.31
    洐
    -1.23
    cution
    -1.21
     geschenk
    -1.17
    蔟
    -1.14
     thép
    -1.11
    varlak
    -1.11
     feb
    -1.08
     くん
    -1.06
    ändigen
    -1.06
    POSITIVE LOGITS
     our
    1.93
     between
    1.67
     their
    1.55
    èvent
    1.34
     アンド
    1.30
     בין
    1.30
    <bos>
    1.29
     greater
    1.27
     other
    1.24
     между
    1.20
    Activations Density 0.034%

    No Known Activations