© 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. 10-GEMMASCOPE-RES-131K
    7. 101252
    Prev
    Next
    INDEX
    Explanations

    fire incidents

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

    The neuron detects mentions of literal fire events—especially occurrences of the word “fire” (and close synonyms like “blaze”) in descriptions of burning incidents.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    er
    -2.72
    (
    -2.55
    s
    -2.48
    k
    -2.45
    ’
    -2.42
    ant
    -2.13
    \
    -2.11
    N
    -2.06
    at
    -2.02
    J
    -1.95
    POSITIVE LOGITS
    }
    2.36
     nové
    2.34
    ቷ
    2.28
     otras
    2.06
     nowych
    2.03
     quieren
    2.02
    ༛
    2.02
    쨩
    1.99
     nuevos
    1.95
    borsa
    1.95
    Activations Density 0.015%

    No Known Activations