© 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. 100235
    Prev
    Next
    INDEX
    Explanations

    calculator

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

    This neuron strongly activates on occurrences of the word “calculator.”

    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
     Approximately
    -2.89
    𖣘
    -2.88
     alguns
    -2.78
     Roughly
    -2.78
     Based
    -2.75
     Around
    -2.67
     algunos
    -2.59
     Utilizing
    -2.56
     Regarding
    -2.55
     Now
    -2.52
    POSITIVE LOGITS
    .
    3.80
    𓋼
    2.64
    ⩴
    2.61
    📞
    2.50
     твои
    2.48
    ☎
    2.48
    도
    2.47
    jewództ
    2.33
    蔸
    2.28
    ſſel
    2.25
    Activations Density 0.003%

    No Known Activations