© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59459
    Prev
    Next
    INDEX
    Explanations

    numbers and specific sequences

    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
    冯
    -0.79
    venu
    -0.72
     locks
    -0.70
    Cheese
    -0.68
    łka
    -0.67
     locked
    -0.66
     {.
    -0.66
     Fair
    -0.66
    vorous
    -0.66
     PRE
    -0.65
    POSITIVE LOGITS
     content
    0.83
    content
    0.77
    文分享
    0.66
    â
    0.65
    uby
    0.63
     conclusion
    0.62
     cathode
    0.62
    万美元
    0.61
     Halter
    0.61
     cognitive
    0.61
    Activations Density 0.080%

    No Known Activations