© 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. 70420
    Prev
    Next
    INDEX
    Explanations

    threat of

    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
    
    -1.45
    The
    -1.42
     ऊ
    -1.30
     bocetos
    -1.30
     chiamato
    -1.30
     أيضًا
    -1.30
     stessa
    -1.30
    еме
    -1.28
     perfectamente
    -1.28
     mijn
    -1.28
    POSITIVE LOGITS
     of
    2.25
     that
    2.06
    沨
    1.52
    idends
    1.51
     further
    1.46
    {
    1.41
     Як
    1.39
     Therefore
    1.38
     additional
    1.33
     oleh
    1.32
    Activations Density 0.015%

    No Known Activations