© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26390
    Prev
    Next
    INDEX
    Explanations

    opposition

    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
    N
    -3.41
    C
    -2.73
     have
    -2.69
    T
    -2.66
    D
    -2.52
    M
    -2.45
    S
    -2.34
    F
    -2.31
     were
    -2.17
     assorted
    -2.14
    POSITIVE LOGITS
    ↵
    3.28
    熜
    2.44
     realizará
    2.38
     presentaron
    2.38
    اً
    2.34
     juger
    2.20
    งิน
    2.11
    ᐕ
    2.08
     cœurs
    2.06
    櫪
    2.05
    Activations Density 0.012%

    No Known Activations