© 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. 95710
    Prev
    Next
    INDEX
    Explanations

    references to tables and 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
    ,
    -1.15
     {
    -1.01
     on
    -0.99
    webtoken
    -0.96
     a
    -0.96
     THAT
    -0.96
    ClassNotFound
    -0.94
     From
    -0.93
    ttes
    -0.93
    cloudy
    -0.91
    POSITIVE LOGITS
    tabular
    1.37
     dotyczą
    1.30
     table
    1.27
    +}$
    1.25
    场比赛
    1.20
     которой
    1.16
     list
    1.15
     values
    1.14
     tables
    1.14
    夀
    1.13
    Activations Density 0.003%

    No Known Activations