© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92143
    Prev
    Next
    INDEX
    Explanations

    power output and handling

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

    The neuron is keyed to detect mathematical/formulaic content—tokens used in equations (e.g. “int,” “frac,” limits, numeric values, units like “power,” “average,” 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_34/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
    𝟙
    -0.85
    گانی
    -0.76
    pH
    -0.73
     cellpadding
    -0.73
    дил
    -0.71
    hibits
    -0.70
     bookId
    -0.69
    productList
    -0.69
    namics
    -0.68
    kran
    -0.68
    POSITIVE LOGITS
     power
    4.41
    power
    3.23
     Power
    3.02
    Power
    2.94
    功率
    2.84
     powers
    2.81
     POWER
    2.75
    POWER
    2.52
     puissance
    2.39
     potenza
    2.39
    Activations Density 0.074%

    No Known Activations