© 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. 73965
    Prev
    Next
    INDEX
    Explanations

    purpose or goal achieved by

    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
    ถ้า
    -1.18
     for
    -1.18
    QPalette
    -1.13
    poň
    -1.13
     if
    -1.11
    สำหรับ
    -1.09
    więcej
    -1.05
     any
    -1.05
    skrä
    -1.04
     just
    -1.02
    POSITIVE LOGITS
     mediante
    1.48
     通过
    1.47
    through
    1.27
    without
    1.27
     VERY
    1.18
     grâce
    1.17
     путем
    1.17
     poprzez
    1.15
     myriad
    1.13
     They
    1.12
    Activations Density 0.045%

    No Known Activations