© 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. 22-GEMMASCOPE-RES-131K
    7. 79762
    Prev
    Next
    INDEX
    Explanations

    codes and file paths

    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_22/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
     would
    -1.80
     style
    -1.48
     but
    -1.41
     this
    -1.36
     while
    -1.30
    MAXN
    -1.30
     his
    -1.30
    (;;)
    -1.30
     "..\..\
    -1.29
     could
    -1.27
    POSITIVE LOGITS
    Stéphane
    1.77
    Condi
    1.37
     accompan
    1.33
     lading
    1.33
     biex
    1.31
    もあるので
    1.30
    Commande
    1.30
    Entrée
    1.29
    Svet
    1.27
    そうに
    1.26
    Activations Density 0.011%

    No Known Activations