© 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. 10-GEMMASCOPE-RES-131K
    7. 130700
    Prev
    Next
    INDEX
    Explanations

    about us sections

    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_10/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
    ográfico
    -1.38
    емы
    -1.35
     AUTHORITIES
    -1.33
    РЫ
    -1.32
     nepiecieš
    -1.27
    ласти
    -1.26
    Bronnen
    -1.25
     июня
    -1.23
    Vorlage
    -1.23
    gemeins
    -1.20
    POSITIVE LOGITS
     which
    1.50
     differs
    1.39
     each
    1.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.32
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.31
     exceeds
    1.27
    ↵↵↵↵↵↵↵↵↵↵↵
    1.27
    \
    1.27
     difference
    1.26
    ↵↵↵↵↵↵↵↵↵↵
    1.25
    Activations Density 0.077%

    No Known Activations