© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48043
    Prev
    Next
    INDEX
    Explanations

    calls to emergency services

    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
     фоне
    -0.86
     JAKARTA
    -0.86
    ABU
    -0.79
    toHaveBeen
    -0.77
    ciuto
    -0.77
    Ecco
    -0.76
     الدرا
    -0.76
     armies
    -0.76
    ná
    -0.75
    CTL
    -0.74
    POSITIVE LOGITS
     calls
    3.27
     call
    3.00
    calls
    2.63
     Calls
    2.47
    Calls
    2.39
    call
    2.36
    Call
    2.16
     Call
    2.05
    CALL
    1.80
     CALL
    1.80
    Activations Density 0.029%

    No Known Activations