© 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. 50428
    Prev
    Next
    INDEX
    Explanations

    door handles and hardware

    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
     Loyal
    -0.78
    ਈ
    -0.74
    ricas
    -0.73
     foldable
    -0.72
     GORDON
    -0.72
    츰
    -0.71
    canf
    -0.70
    గు
    -0.69
    Gordon
    -0.69
    引导
    -0.69
    POSITIVE LOGITS
     handles
    2.00
     hardware
    1.84
     handle
    1.79
    Handles
    1.73
     knobs
    1.66
    hardware
    1.65
    handle
    1.59
    handles
    1.58
     Handles
    1.54
    Handle
    1.52
    Activations Density 0.023%

    No Known Activations