© 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. 82433
    Prev
    Next
    INDEX
    Explanations

    [word] off

    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
     Outsider
    -0.85
    Upstream
    -0.81
    ട്ട
    -0.80
    ändig
    -0.79
    hematics
    -0.79
     permettra
    -0.78
     puestos
    -0.77
    esser
    -0.76
    ével
    -0.75
     rendono
    -0.75
    POSITIVE LOGITS
     off
    8.69
    off
    5.41
    Off
    5.06
     Off
    4.50
     OFF
    4.06
    OFF
    3.69
    オフ
    3.23
    offs
    3.06
     offs
    3.05
    toff
    2.66
    Activations Density 0.155%

    No Known Activations