© 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. 35520
    Prev
    Next
    INDEX
    Explanations

    activities / processes

    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
    ambassade
    -1.33
     высокая
    -1.31
     отличаются
    -1.25
     desnuda
    -1.23
    そこ
    -1.23
     extremadamente
    -1.23
    Asie
    -1.19
    lial
    -1.19
     asegurarse
    -1.19
     comprobar
    -1.18
    POSITIVE LOGITS
     of
    2.98
     the
    1.48
     của
    1.28
    畕
    1.28
     conector
    1.24
    nyata
    1.23
    鱟
    1.20
     dager
    1.19
     monstre
    1.17
    ojos
    1.16
    Activations Density 0.115%

    No Known Activations