© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    classical learning and convergence

    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
     misst
    -1.41
    
    -1.40
    ishment
    -1.35
    鮰
    -1.32
    iosync
    -1.32
     louer
    -1.31
    桕
    -1.31
    ⢫
    -1.26
    
    -1.26
     confirme
    -1.26
    POSITIVE LOGITS
     with
    1.66
     or
    1.48
     in
    1.29
     even
    1.29
     often
    1.28
     for
    1.24
     \
    1.22
     to
    1.20
     There
    1.19
    1.18
    Activations Density 0.107%
    No Known Activations