© 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. 78884
    Prev
    Next
    INDEX
    Explanations

    radar detection and traffic enforcement

    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
     pinterest
    -0.81
     segreg
    -0.80
     Anspruch
    -0.78
    чное
    -0.78
    Русский
    -0.77
    賊
    -0.77
    Història
    -0.76
     segregation
    -0.75
    儡
    -0.74
    personen
    -0.73
    POSITIVE LOGITS
     radar
    2.31
     Radar
    1.96
    radar
    1.93
    Radar
    1.82
     рада
    1.34
     clocked
    1.22
     detector
    1.18
     laser
    1.17
     rada
    1.12
     RAD
    1.07
    Activations Density 0.015%

    No Known Activations