© 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. 65452
    Prev
    Next
    INDEX
    Explanations

    recognizing approximations

    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
     السياس
    -1.30
     trám
    -1.16
     geplant
    -1.16
     écouter
    -1.16
    킁
    -1.15
     décider
    -1.09
    柔ら
    -1.06
     specif
    -1.06
     quatre
    -1.03
    utiliz
    -1.03
    POSITIVE LOGITS
     only
    1.67
     ONLY
    1.41
     for
    1.41
     although
    1.38
     until
    1.34
     Although
    1.33
     allows
    1.26
     focusing
    1.25
     Despite
    1.25
     despite
    1.25
    Activations Density 0.052%

    No Known Activations