© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    like it was

    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
     that
    -2.34
     if
    -2.20
     have
    -2.16
     are
    -2.05
    this
    -1.84
    if
    -1.78
     can
    -1.73
     should
    -1.73
     must
    -1.69
    ?
    -1.69
    POSITIVE LOGITS
     varier
    1.64
    
    1.57
     legendar
    1.56
     auster
    1.55
    sowie
    1.55
     vinos
    1.52
     zodia
    1.52
    🌬
    1.51
     bandeau
    1.51
     accepter
    1.51
    Activations Density 0.082%

    No Known Activations