© 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. 27993
    Prev
    Next
    INDEX
    Explanations

    numbers and code 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
     Despite
    -1.08
     Originally
    -1.07
     some
    -1.07
     Some
    -1.02
     Several
    -1.01
     and
    -0.99
    !（
    -0.99
    ()");
    -0.98
     gave
    -0.98
     catalana
    -0.98
    POSITIVE LOGITS
     hà
    1.19
    بله
    1.16
    THEN
    1.16
     cóc
    1.13
     gerar
    1.13
     NSCoder
    1.11
     meditación
    1.11
     chua
    1.11
     conceptos
    1.10
     personalización
    1.10
    Activations Density 0.001%

    No Known Activations