© 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. 34-GEMMASCOPE-RES-131K
    7. 106893
    Prev
    Next
    INDEX
    Explanations

    battery charging and saving

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

    The neuron activates on mentions of device power or battery status—e.g. “power,” “battery,” “charging,” and related system‐path tokens.

    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
     bandwidth
    -0.81
    Beer
    -0.79
     Beer
    -0.74
    银行
    -0.72
     CITES
    -0.71
    铢
    -0.71
     EdgeInsets
    -0.71
    Bandwidth
    -0.70
     "','
    -0.70
    емое
    -0.69
    POSITIVE LOGITS
    Plug
    0.97
    plugged
    0.90
     Coul
    0.83
    Coupons
    0.78
     unplug
    0.78
     整理
    0.77
    ăm
    0.77
    PLUG
    0.75
    RITION
    0.75
     Plu
    0.75
    Activations Density 0.006%

    No Known Activations