© 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. 84529
    Prev
    Next
    INDEX
    Explanations

    Congress, governments, media actions

    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
     from
    -1.38
     that
    -1.27
     with
    -1.19
    llten
    -1.13
     between
    -1.12
    RESUMEN
    -1.10
     while
    -1.09
     at
    -1.09
     Ähn
    -1.09
    痪
    -1.08
    POSITIVE LOGITS
     Bajos
    1.47
     coreano
    1.25
     temporaire
    1.24
     שנים
    1.18
     decisivo
    1.17
    ఝ
    1.16
     tramonto
    1.15
     słoń
    1.14
     competitivo
    1.14
    unately
    1.12
    Activations Density 0.059%

    No Known Activations