© 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. 27985
    Prev
    Next
    INDEX
    Explanations

    words following spelling and screening

    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
     according
    -1.26
    Find
    -1.09
     into
    -1.05
    un
    -0.96
    end
    -0.93
    GRAFÍA
    -0.88
     up
    -0.88
     unwarranted
    -0.87
    According
    -0.86
     under
    -0.86
    POSITIVE LOGITS
     which
    1.73
     being
    1.63
     that
    1.61
     που
    1.59
     možnosti
    1.46
     ועל
    1.41
     possibilities
    1.27
     mahdollis
    1.23
     که
    1.22
     mulig
    1.22
    Activations Density 0.122%

    No Known Activations