© 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. 59135
    Prev
    Next
    INDEX
    Explanations

    Smart LiPo Technology

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

    This neuron detects technical specification numbers and their associated units (e.g. amps, volts, C-ratings, kV) in product descriptions.

    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
    ܨ
    -0.77
    emic
    -0.73
     پز
    -0.72
     iPod
    -0.71
     vali
    -0.71
    渺
    -0.71
    öy
    -0.71
    検討
    -0.67
    zoll
    -0.66
     ermöglichen
    -0.64
    POSITIVE LOGITS
     ESC
    1.63
    ESC
    1.44
     esc
    1.38
     motor
    1.30
     Castle
    1.16
     lipos
    1.03
     lipo
    1.03
    Castle
    0.97
     Lipo
    0.94
     Motor
    0.92
    Activations Density 0.018%

    No Known Activations