© 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. 10-GEMMASCOPE-RES-131K
    7. 44796
    Prev
    Next
    INDEX
    Explanations

    events and projects

    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_10/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
     coś
    -1.41
    pantalon
    -1.30
    </h2>
    -1.28
     bahkan
    -1.27
    ,
    -1.27
    chaussure
    -1.25
     donde
    -1.24
    </strong>
    -1.22
    見ても
    -1.22
     conflictos
    -1.20
    POSITIVE LOGITS
    我们
    1.33
    七月
    1.27
    二月
    1.22
    三月
    1.20
    ‼
    1.18
    ﹞
    1.17
    ytet
    1.16
    いよいよ
    1.13
     berikutnya
    1.11
     lames
    1.11
    Activations Density 0.279%

    No Known Activations