© 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. 109010
    Prev
    Next
    INDEX
    Explanations

    fire extinguishing equipment

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

    firefighting and suppression

    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
    檐
    0.46
    뉘
    0.44
    മ്പർ
    0.44
    Reconnect
    0.43
    цкі
    0.42
    采访
    0.41
    udio
    0.41
     transceiver
    0.41
     پروت
    0.40
    桥
    0.39
    POSITIVE LOGITS
     firefighting
    0.68
     extinguishers
    0.63
     extinguishing
    0.63
     nước
    0.62
     தண்ணீர்
    0.58
     water
    0.56
    firetruck
    0.56
     extinguisher
    0.55
     Fire
    0.55
     वाटर
    0.55
    Activations Density 0.026%

    No Known Activations