© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90760
    Prev
    Next
    INDEX
    Explanations

    descriptions of appearance and function

    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
     or
    -2.59
     to
    -2.14
     but
    -2.06
     in
    -2.03
     however
    -1.78
    However
    -1.71
     jedoch
    -1.55
     of
    -1.52
     as
    -1.50
    but
    -1.45
    POSITIVE LOGITS
    hmig
    1.55
    謦
    1.49
    ༷
    1.45
     ڤ
    1.40
    reportWebVitals
    1.39
    äsenti
    1.36
    夘
    1.36
     bobina
    1.33
     dagar
    1.33
     dinam
    1.33
    Activations Density 0.038%

    No Known Activations