© 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. 95636
    Prev
    Next
    INDEX
    Explanations

    reporting statements of fact

    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
     therefore
    -1.48
     also
    -1.17
     then
    -1.16
     thus
    -1.08
     for
    -1.05
     ۱۳
    -1.01
     главным
    -1.00
     hence
    -0.98
     ...
    -0.97
     quindi
    -0.97
    POSITIVE LOGITS
     ابتدا
    1.26
    簡單
    1.22
    号線
    1.17
     徒歩
    1.17
    kezett
    1.16
    According
    1.14
    ってみました
    1.13
    ELES
    1.12
     информация
    1.12
     first
    1.12
    Activations Density 0.074%

    No Known Activations