© 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. 10-GEMMASCOPE-RES-131K
    7. 130950
    Prev
    Next
    INDEX
    Explanations

    error messages and invalid parameters

    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_10/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
    trying
    -2.30
     Dinas
    -2.23
    primarily
    -2.09
    probably
    -2.09
    certainly
    -2.06
    somewhat
    -2.06
    really
    -2.00
    larg
    -1.99
    unfortunately
    -1.92
     famoso
    -1.91
    POSITIVE LOGITS
     new
    2.34
    Some
    2.13
     because
    2.13
     despite
    2.05
     Despite
    2.02
     while
    2.02
    Despite
    1.97
     Some
    1.95
     provide
    1.90
     ....
    1.87
    Activations Density 0.020%

    No Known Activations