© 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. 79958
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
     in
    -1.37
     alábbi
    -1.33
    Gruss
    -1.27
     arquivos
    -1.26
     on
    -1.23
     pengobatan
    -1.23
     öğretmen
    -1.18
     Traité
    -1.17
     Coloque
    -1.17
    дарь
    -1.16
    POSITIVE LOGITS
     that
    1.63
    無い
    1.37
    %;
    1.27
    なのかな
    1.26
    様々
    1.21
    我们会
    1.17
    ==""){
    1.15
    んですよ
    1.11
    P
    1.09
     Urheber
    1.08
    Activations Density 0.004%

    No Known Activations