© 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. 22-GEMMASCOPE-RES-131K
    4. 71253
    Prev
    Next
    INDEX
    Explanations

    Q and A pairs

    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
    utilise
    -1.05
     fonde
    -0.98
     its
    -0.95
    のでしょうか
    -0.93
     imaginar
    -0.91
    andeep
    -0.90
     nasceu
    -0.90
    感じで
    -0.90
     dança
    -0.90
    elang
    -0.90
    POSITIVE LOGITS
     of
    0.99
    Чтобы
    0.97
     on
    0.92
     but
    0.91
    幟
    0.90
     with
    0.86
    県の
    0.85
     command
    0.84
    ğına
    0.84
    ่านั้น
    0.82
    Activations Density 0.000%

    No Known Activations