© 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. 64493
    Prev
    Next
    INDEX
    Explanations

    fire fighters and fire service

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

    firefighter and fire department

    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
    FBSDKInternal
    0.46
    onnements
    0.44
     seroton
    0.43
    ndvi
    0.42
     cerebrospinal
    0.42
     moder
    0.41
    )};
    0.40
     cerevisiae
    0.40
    ραπε
    0.40
    <body>
    0.40
    POSITIVE LOGITS
     firefighter
    1.22
     firefighting
    1.18
     firefighters
    1.16
    消防
    1.13
     fireman
    1.11
     Fire
    1.05
    🚒
    1.05
     फायर
    1.01
     fire
    0.98
    Fire
    0.97
    Activations Density 0.061%

    No Known Activations