© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98939
    Prev
    Next
    INDEX
    Explanations

    alkaline batteries

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

    references to batteries and battery-related technology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of power sources—especially batteries and their specifications (types, counts, voltages, 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
    Willy
    -0.84
    大王
    -0.73
     Lungen
    -0.70
    魅
    -0.69
     Willy
    -0.69
     Hinsicht
    -0.68
     trăm
    -0.67
    Telefono
    -0.67
    chtend
    -0.66
     gentlemen
    -0.65
    POSITIVE LOGITS
     batteries
    3.23
     Batteries
    2.50
    Batteries
    2.19
     AAA
    2.08
    batter
    2.06
     battery
    2.02
     AA
    1.99
     бата
    1.79
     Battery
    1.75
     baterías
    1.72
    Activations Density 0.019%

    No Known Activations