© 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. 13039
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     dát
    -1.09
    ocd
    -1.05
    diseño
    -1.05
    keletal
    -1.05
    感じが
    -1.04
    during
    -1.04
    langsung
    -1.03
    coleccion
    -1.02
     inaprop
    -1.02
    faatkan
    -1.02
    POSITIVE LOGITS
     with
    1.26
     (
    1.24
     out
    1.15
     as
    1.07
     of
    1.02
     new
    1.02
     more
    1.02
     on
    1.00
     so
    0.97
    (@"%@",
    0.97
    Activations Density 0.000%

    No Known Activations