© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    categories and divisions

    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
     during
    -1.60
     on
    -1.55
    
    -1.42
    𖡼
    -1.34
    ợn
    -1.32
    calaureate
    -1.30
     getopt
    -1.27
    玑
    -1.27
    ࿆
    -1.26
    takers
    -1.24
    POSITIVE LOGITS
     of
    2.30
     such
    1.58
     then
    1.33
    コットン
    1.31
     gleiche
    1.30
     why
    1.29
     are
    1.28
     esche
    1.27
     scintill
    1.27
     secteurs
    1.27
    Activations Density 0.182%

    No Known Activations