© 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. 74945
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     sentirse
    -1.23
    iaal
    -1.20
     soñar
    -1.19
    rimin
    -1.16
     akzep
    -1.15
     mantenerse
    -1.13
     hacerte
    -1.13
     agradável
    -1.13
     registró
    -1.13
    文分享
    -1.13
    POSITIVE LOGITS
     because
    1.20
     with
    1.20
    헷
    1.10
     from
    1.09
     endast
    0.99
     in
    0.96
     only
    0.93
     on
    0.93
     alltså
    0.91
    يمي
    0.90
    Activations Density 0.117%

    No Known Activations