© 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. 67526
    Prev
    Next
    INDEX
    Explanations

    independent evaluations

    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
     творо
    -0.99
    ,
    -0.84
    向了
    -0.82
    keterangan
    -0.81
    jahre
    -0.81
    jei
    -0.81
    nements
    -0.80
     respectivamente
    -0.79
    ulle
    -0.79
    局长
    -0.79
    POSITIVE LOGITS
     figlio
    0.99
     using
    0.96
     passent
    0.95
     thoroughly
    0.94
     thorough
    0.93
     nahilalakip
    0.92
    昨日の
    0.91
     determining
    0.91
    ācijas
    0.89
     effettu
    0.88
    Activations Density 0.145%

    No Known Activations