© 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. 34-GEMMASCOPE-RES-131K
    4. 60489
    Prev
    Next
    INDEX
    Explanations

    lead acid battery

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

    The neuron specifically fires on numeric specification tokens (e.g. digit sequences and unit symbols like “V” or “Ah”) in technical battery or LED power‐rating contexts.

    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
    paration
    -0.80
     czuj
    -0.79
    小结
    -0.73
    нное
    -0.73
     Lilli
    -0.71
     桂
    -0.70
     Walkover
    -0.69
     manuales
    -0.68
    educt
    -0.67
    roquia
    -0.67
    POSITIVE LOGITS
     AGM
    1.35
    AGM
    1.30
     acid
    0.95
    gel
    0.91
    Gel
    0.86
     GEL
    0.86
     absorbent
    0.85
    Ah
    0.85
    acid
    0.85
     Ah
    0.84
    Activations Density 0.015%

    No Known Activations