© 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. 95833
    Prev
    Next
    INDEX
    Explanations

    places and technical terms

    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
    why
    -1.26
     what
    -1.25
     why
    -1.23
     these
    -1.13
     Why
    -1.09
    Why
    -1.09
     and
    -1.05
    what
    -1.04
       
    -1.02
     how
    -1.02
    POSITIVE LOGITS
     Meksika
    1.16
    Ambiente
    1.14
    Capacidad
    1.14
    Fotografía
    1.14
     MUNDO
    1.13
    damit
    1.13
     morgens
    1.13
     brukar
    1.12
     prét
    1.12
    Especificaciones
    1.12
    Activations Density 0.059%

    No Known Activations