© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    not just a specific example

    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
    Ꮨ
    -1.64
     informatie
    -1.58
     olmaz
    -1.55
     baloncesto
    -1.53
     
    -1.52
    figurine
    -1.51
    bikini
    -1.50
     gastos
    -1.50
     bilgiler
    -1.48
     eğer
    -1.48
    POSITIVE LOGITS
    from
    2.41
    which
    2.25
    and
    2.19
    including
    2.00
    s
    1.96
    st
    1.95
    no
    1.88
    v
    1.83
    2
    1.80
    by
    1.77
    Activations Density 0.009%

    No Known Activations