© 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. 115872
    Prev
    Next
    INDEX
    Explanations

    programming namespaces and libraries

    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
     not
    -1.66
     by
    -1.63
     on
    -1.60
     with
    -1.59
     at
    -1.56
     any
    -1.53
     new
    -1.52
     so
    -1.52
     in
    -1.48
     just
    -1.47
    POSITIVE LOGITS
     delightfully
    1.83
     acclaimed
    1.77
     strikingly
    1.74
     Dinas
    1.71
     amazingly
    1.70
     exceptionally
    1.69
     mediocre
    1.63
     colossal
    1.62
     ridiculously
    1.60
     alluring
    1.60
    Activations Density 0.055%

    No Known Activations