© 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. 34-GEMMASCOPE-RES-131K
    7. 108954
    Prev
    Next
    INDEX
    Explanations

    fire, emergency, escape, evacuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    yac
    -0.85
    NaCl
    -0.78
    轢
    -0.75
    ٧
    -0.74
    IRY
    -0.74
    ٨
    -0.74
    拦截
    -0.73
    ssid
    -0.73
    campista
    -0.73
    ablon
    -0.72
    POSITIVE LOGITS
     fire
    3.77
     Fire
    3.05
    fire
    2.75
    Fire
    2.66
     emergency
    2.30
     exit
    2.25
    FIRE
    2.20
     evacuation
    2.13
     FIRE
    2.13
     exits
    2.09
    Activations Density 0.028%

    No Known Activations