© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33327
    Prev
    Next
    INDEX
    Explanations

    fire and explosion

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

    The neuron responds to technical safety‐and‐regulatory terminology—particularly classification codes, standard names, and compliance tokens in industrial electrical safety documents.

    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
    OGND
    -0.82
     Dick
    -0.78
    랜드
    -0.77
     guter
    -0.76
     sostener
    -0.76
    Sea
    -0.74
    omla
    -0.74
    Espagne
    -0.74
    iron
    -0.73
     pequeno
    -0.73
    POSITIVE LOGITS
     explosion
    1.08
    Explosion
    0.97
     Explosion
    0.97
     Atmos
    0.93
     Explosive
    0.93
     flame
    0.88
    dust
    0.86
    Atmos
    0.84
    explosion
    0.82
     Flame
    0.81
    Activations Density 0.014%

    No Known Activations