© 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. 73166
    Prev
    Next
    INDEX
    Explanations

    wattage values

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

    The neuron activates on numeric power‐level specifications in watts (e.g. “W,” “watt,” “watts”).

    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
    哢
    -2.02
    儅
    -1.77
    尽可能
    -1.66
     detalj
    -1.61
     siguran
    -1.57
     masina
    -1.56
     prêts
    -1.55
     retras
    -1.54
     stanga
    -1.52
     waarvan
    -1.52
    POSITIVE LOGITS
    ER
    1.89
    END
    1.80
    following
    1.70
     актуаль
    1.67
    EL
    1.67
    síða
    1.66
     interplay
    1.64
    ES
    1.64
    ED
    1.61
    цы
    1.59
    Activations Density 0.005%

    No Known Activations