© 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. 66424
    Prev
    Next
    INDEX
    Explanations

    equations with variables

    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
     if
    -1.40
     first
    -1.28
    。　
    -1.20
     for
    -1.18
     evidently
    -1.16
     had
    -1.09
     notably
    -1.08
         
    -1.06
     seemingly
    -1.06
     invariably
    -1.04
    POSITIVE LOGITS
     portefeuille
    1.31
     fidé
    1.31
     piensan
    1.27
     célè
    1.23
    Gön
    1.21
    Zdrav
    1.21
    oulos
    1.19
    pendentif
    1.17
     satisfacer
    1.16
     corriger
    1.16
    Activations Density 0.001%

    No Known Activations