© 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. 31153
    Prev
    Next
    INDEX
    Explanations

    smart lighting and controls

    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
    getKeyCode
    -0.81
    ürtel
    -0.77
    吏
    -0.74
    ḃ
    -0.72
    ilya
    -0.71
    messaging
    -0.71
     инструменты
    -0.70
     الاعت
    -0.69
    )(-
    -0.69
     messaging
    -0.69
    POSITIVE LOGITS
     Hue
    0.89
    Hue
    0.87
     Philips
    0.82
     Kipling
    0.81
     Bridge
    0.81
     escenas
    0.80
    CIE
    0.80
     dimmer
    0.80
     dimming
    0.80
    CTL
    0.79
    Activations Density 0.004%

    No Known Activations