© 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. 129118
    Prev
    Next
    INDEX
    Explanations

    python future imports

    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
    Zubereitung
    -1.35
     bénévol
    -1.33
    Salu
    -1.21
     насеље
    -1.20
    توضیحات
    -1.17
     trésor
    -1.16
     gouverneur
    -1.16
     désir
    -1.16
    Kommentare
    -1.15
    TRIBUN
    -1.14
    POSITIVE LOGITS
     such
    1.41
    !
    1.27
     and
    1.18
     this
    1.16
    んだろう
    1.07
    &
    1.07
     everything
    1.06
     what
    1.00
    。
    0.98
     like
    0.98
    Activations Density 0.003%

    No Known Activations