© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14568
    Prev
    Next
    INDEX
    Explanations

    configuration and code structures

    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
     as
    -1.13
     It
    -1.09
     to
    -1.09
     all
    -1.05
     there
    -1.01
    to
    -1.00
     what
    -0.99
     has
    -0.98
     some
    -0.98
     h
    -0.96
    POSITIVE LOGITS
     serre
    1.27
    傒
    1.18
     hydrauli
    1.16
    если
    1.13
     peluche
    1.13
     Toujours
    1.10
     Dép
    1.09
     marte
    1.09
     Avec
    1.08
     persiste
    1.08
    Activations Density 0.060%

    No Known Activations