© 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. 26111
    Prev
    Next
    INDEX
    Explanations

    second, third, or fourth item

    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
    depuis
    -1.39
    wasn
    -1.30
     MAKES
    -1.28
    doesn
    -1.27
     toutefois
    -1.22
    Rha
    -1.21
    ミカ
    -1.21
    didn
    -1.19
     nuevos
    -1.18
     appré
    -1.16
    POSITIVE LOGITS
     this
    1.29
     when
    1.27
     and
    1.15
     because
    1.10
     after
    1.09
    Writer
    1.05
     should
    1.04
     și
    1.03
     a
    1.02
    ⃣
    1.02
    Activations Density 0.019%

    No Known Activations