© 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. 38237
    Prev
    Next
    INDEX
    Explanations

    path and key binding

    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
    pFile
    -0.82
    kään
    -0.75
    ukka
    -0.73
    icznej
    -0.72
    ∬
    -0.72
    magitan
    -0.67
     Juventud
    -0.67
     repositories
    -0.66
     fichier
    -0.65
    qua
    -0.65
    POSITIVE LOGITS
     path
    4.66
    path
    4.09
    Path
    3.86
     Path
    3.78
     paths
    3.63
    路径
    3.14
    PATH
    3.09
    paths
    2.97
     PATH
    2.92
     pathway
    2.81
    Activations Density 0.096%

    No Known Activations