© 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. 93900
    Prev
    Next
    INDEX
    Explanations

    # context, James, PT, 5

    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
     tslint
    -0.96
     ?',
    -0.91
     traktor
    -0.86
     IAAF
    -0.86
     Syrian
    -0.84
     Ebola
    -0.84
    冈
    -0.80
     didik
    -0.79
     ২০১
    -0.79
    ancers
    -0.78
    POSITIVE LOGITS
     metaverse
    1.01
    strncmp
    0.95
     Covid
    0.95
     vaccine
    0.92
    出口
    0.90
     covid
    0.87
     ২০
    0.84
     Stell
    0.82
    androidx
    0.78
     Impf
    0.77
    Activations Density 0.000%

    No Known Activations