© 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. 57774
    Prev
    Next
    INDEX
    Explanations

    call, data, Court, Router

    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
    Stroke
    -0.76
     INTERFACE
    -0.75
     Stroke
    -0.75
     Dose
    -0.75
    Dose
    -0.73
     Deacon
    -0.69
    苄
    -0.68
    KeepAlive
    -0.68
    烤
    -0.68
    Clicked
    -0.67
    POSITIVE LOGITS
    Acknowled
    0.64
    isFull
    0.62
    øm
    0.61
    ális
    0.60
     Bong
    0.60
    ことはありません
    0.60
    劣
    0.60
     Bunting
    0.59
    firmasi
    0.59
     Combination
    0.59
    Activations Density 0.081%

    No Known Activations