© 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. 68003
    Prev
    Next
    INDEX
    Explanations

    code structures and identifiers

    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
     triko
    -1.39
     bluz
    -1.26
     grises
    -1.25
     dekol
    -1.24
    Ă
    -1.19
     parfü
    -1.17
     silikon
    -1.16
     приготовления
    -1.16
     farbe
    -1.14
     parfüm
    -1.13
    POSITIVE LOGITS
     then
    1.33
     подходит
    1.05
     omicron
    1.03
     όμως
    1.02
     coar
    1.01
     uncin
    1.01
    Fonto
    1.00
     incursion
    1.00
     disreg
    0.98
     isole
    0.98
    Activations Density 0.049%

    No Known Activations