© 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. 101839
    Prev
    Next
    INDEX
    Explanations

    parts of words, numbers, punctuation

    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
     “
    -1.54
     (
    -1.50
     greatly
    -1.41
     helped
    -1.41
     doing
    -1.41
     truly
    -1.40
     has
    -1.39
     utterly
    -1.39
     essentially
    -1.39
     helping
    -1.38
    POSITIVE LOGITS
     nieuwe
    1.57
    
    1.51
     ganadores
    1.51
    crimination
    1.48
     of
    1.45
     jednym
    1.45
    according
    1.40
    naments
    1.38
    namiento
    1.35
     viejos
    1.34
    Activations Density 0.056%

    No Known Activations