© 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. 90073
    Prev
    Next
    INDEX
    Explanations

    Chrysler, Ford, Husband, Q:, // Copyright

    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
    SORT
    -0.80
     quarry
    -0.80
     japanese
    -0.79
    positions
    -0.79
     DDT
    -0.77
     Score
    -0.75
    igshid
    -0.75
    蹙
    -0.75
    телите
    -0.75
    zeum
    -0.74
    POSITIVE LOGITS
    izzi
    0.79
     带
    0.79
     hemi
    0.71
    疋
    0.68
     चे
    0.67
    怀
    0.66
    valentino
    0.65
     Hohen
    0.65
    滸
    0.64
    مدر
    0.62
    Activations Density 0.024%

    No Known Activations