© 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. 70851
    Prev
    Next
    INDEX
    Explanations

    future events or obligations

    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
     flota
    -1.04
     azonban
    -1.04
    Masukkan
    -1.02
    tismo
    -1.02
    Ār
    -1.00
     Após
    -1.00
    peluche
    -1.00
     artesanato
    -0.98
     після
    -0.97
    Actualmente
    -0.97
    POSITIVE LOGITS
     will
    1.27
     would
    1.06
     it
    1.02
     wtedy
    1.00
     quick
    0.99
     then
    0.98
    return
    0.97
    すぐ
    0.94
    printStackTrace
    0.91
     still
    0.90
    Activations Density 0.067%

    No Known Activations