© 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. 59099
    Prev
    Next
    INDEX
    Explanations

    expressing desire or intention

    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
     bakom
    -1.67
     connais
    -1.50
    </h2>
    -1.49
     hjälper
    -1.48
     ingår
    -1.47
     fungerar
    -1.45
     utanför
    -1.45
    ))}
    -1.45
     tillgäng
    -1.44
     dessutom
    -1.43
    POSITIVE LOGITS
     you
    2.06
     if
    2.00
     to
    1.88
    ’
    1.76
    ſſen
    1.34
     sofern
    1.29
     отличаются
    1.27
    esercito
    1.27
     получают
    1.27
     derer
    1.25
    Activations Density 0.050%

    No Known Activations