© 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. 2441
    Prev
    Next
    INDEX
    Explanations

    protobuf, api, data structures

    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
    jdons
    -0.73
    ulte
    -0.73
    ්‍ර
    -0.72
    דים
    -0.71
     Gaston
    -0.70
     Muffins
    -0.69
     buah
    -0.69
     Standing
    -0.68
     MSR
    -0.68
     alight
    -0.67
    POSITIVE LOGITS
    oneof
    0.95
    otek
    0.90
    createTime
    0.85
    nity
    0.81
    displayName
    0.79
    rieved
    0.79
    nii
    0.78
     sacré
    0.77
    Vegeu
    0.76
     Latham
    0.76
    Activations Density 0.015%

    No Known Activations