© 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. 130354
    Prev
    Next
    INDEX
    Explanations

    numbers and entities

    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
     to
    -0.89
     let
    -0.82
     in
    -0.82
    いただきます
    -0.80
     or
    -0.79
     has
    -0.79
     will
    -0.78
     is
    -0.78
     starts
    -0.78
     by
    -0.77
    POSITIVE LOGITS
     parfüm
    1.13
     étroite
    1.11
     Perſ
    1.08
     journaux
    1.01
     leſs
    1.01
    categorized
    0.96
     sèche
    0.95
     ſever
    0.94
     kazak
    0.93
     extré
    0.92
    Activations Density 0.173%

    No Known Activations