© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95851
    Prev
    Next
    INDEX
    Explanations

    clause, subdivision, chapter, class

    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
     as
    -1.22
     from
    -1.20
    Также
    -1.09
     тема
    -1.09
     during
    -1.08
    Хотя
    -1.07
     could
    -1.05
    ၈
    -1.05
     поставки
    -1.05
     Perhaps
    -1.03
    POSITIVE LOGITS
    様です
    1.43
    耵
    1.27
     hunne
    1.23
     voisins
    1.21
     fiets
    1.21
     colonnes
    1.21
     zwart
    1.20
     droog
    1.19
    ఽ
    1.18
     ")");
    1.16
    Activations Density 0.003%

    No Known Activations