© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120058
    Prev
    Next
    INDEX
    Explanations

    battery powered and battery life

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

    The neuron activates on mentions of battery-powered features or power supply details.

    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
    or
    -2.17
    ol
    -2.13
    ate
    -2.02
    st
    -2.00
    er
    -1.95
    an
    -1.87
    E
    -1.87
    '
    -1.86
    j
    -1.85
    ly
    -1.77
    POSITIVE LOGITS
     we
    1.79
     ajustar
    1.77
     veremos
    1.73
     consideramos
    1.70
    mları
    1.66
    訁
    1.64
    КОВ
    1.60
    我們的
    1.60
     energii
    1.60
     provocar
    1.59
    Activations Density 0.010%

    No Known Activations