© 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. 68283
    Prev
    Next
    INDEX
    Explanations

    JS/JP/JG jumps

    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
     in
    -1.49
     because
    -1.27
     as
    -1.20
    %@",
    -1.17
     when
    -1.15
     by
    -1.07
     so
    -1.06
     that
    -1.06
     until
    -1.06
     również
    -1.05
    POSITIVE LOGITS
     ทั้ง
    1.13
     später
    1.13
     forbidding
    1.06
    COMO
    1.04
     anstatt
    1.02
    роваться
    1.02
    Baik
    1.02
    érèse
    1.02
     nombreuses
    1.01
    hijo
    1.01
    Activations Density 0.046%

    No Known Activations