© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93412
    Prev
    Next
    INDEX
    Explanations

    emergency call

    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
     leaving
    -0.80
     disappeared
    -0.75
    acana
    -0.73
     附
    -0.73
     standing
    -0.71
     容量
    -0.71
     conducted
    -0.71
     hiding
    -0.70
    circular
    -0.70
     zodiaco
    -0.69
    POSITIVE LOGITS
     emergency
    2.08
    emergency
    1.78
     Emergency
    1.60
    Emergency
    1.60
     EMERGENCY
    1.45
    EMERGENCY
    1.28
     call
    1.20
     emergencies
    1.16
     calls
    1.15
     emer
    1.13
    Activations Density 0.016%

    No Known Activations