© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    domain names

    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
     življen
    -1.23
     mochilas
    -1.21
    確認ください
    -1.21
     aussitôt
    -1.20
     سپس
    -1.16
     stolet
    -1.14
     Tämä
    -1.12
     velik
    -1.11
    řské
    -1.11
     aún
    -1.09
    POSITIVE LOGITS
     how
    1.38
    的是
    1.09
     system
    1.02
    ,
    1.02
     use
    1.02
    </em>
    0.96
     variable
    0.96
     categor
    0.96
     Variable
    0.96
    и
    0.95
    Activations Density 0.054%

    No Known Activations