© 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. 49569
    Prev
    Next
    INDEX
    Explanations

    lead-acid battery

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

    The neuron fires strongly on the formal, highly repetitive phrasing of technical patent‐style descriptions (e.g. “the … is …,” component names, specifications, and numerical references).

    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
    青春
    -0.72
     sympathies
    -0.72
    eterangan
    -0.71
    ife
    -0.71
     unsus
    -0.70
     fijo
    -0.69
    Memor
    -0.69
     ribos
    -0.68
    opress
    -0.66
    嘴里
    -0.66
    POSITIVE LOGITS
     battery
    2.05
     batteries
    1.87
    battery
    1.63
     Battery
    1.63
    Battery
    1.59
     Batteries
    1.49
     BATTERY
    1.40
    电池
    1.34
    Batteries
    1.31
     batterie
    1.29
    Activations Density 0.065%

    No Known Activations