© 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. 66620
    Prev
    Next
    INDEX
    Explanations

    direct and explicit statements

    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
    otriz
    -1.54
     rowspan
    -1.47
     anivers
    -1.44
     conster
    -1.38
    ÉL
    -1.38
     naturel
    -1.34
     dades
    -1.34
     炖
    -1.33
     DÉ
    -1.31
    鹩
    -1.31
    POSITIVE LOGITS
     mehrfach
    1.27
     schlechter
    1.22
     direta
    1.15
     Шаг
    1.11
     verschied
    1.09
    '
    1.09
     dedicada
    1.07
     numerosas
    1.07
     explicitly
    1.05
     avowed
    1.05
    Activations Density 0.040%

    No Known Activations