© 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. 127322
    Prev
    Next
    INDEX
    Explanations

    code annotations

    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
    Лечение
    -1.52
    我们的
    -1.49
    我們的
    -1.45
    しくは
    -1.41
    していた
    -1.38
    You
    -1.38
     потрібно
    -1.36
     their
    -1.34
    また
    -1.31
     знаешь
    -1.31
    POSITIVE LOGITS
     Ã
    1.63
     -"
    1.61
     lanç
    1.59
     andare
    1.49
     interrump
    1.46
    錸
    1.45
     XXXIII
    1.43
     cial
    1.41
     decidedly
    1.40
    ſo
    1.38
    Activations Density 0.006%

    No Known Activations