© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16089
    Prev
    Next
    INDEX
    Explanations

    wildfire and fire events

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

    wildfire and fire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     व्यंजन
    0.45
    ཨ
    0.43
    笵
    0.43
     वस्त्र
    0.42
    款式
    0.42
    allaitement
    0.41
     Bathroom
    0.41
     Dél
    0.41
    Transaksi
    0.40
    褴
    0.40
    POSITIVE LOGITS
     firefighting
    1.12
     wildfire
    1.05
     firefighters
    1.02
     firefighter
    1.02
     wildfires
    0.93
     fire
    0.88
    消防
    0.86
     incênd
    0.82
     kebakaran
    0.80
     flames
    0.80
    Activations Density 0.042%

    No Known Activations