© 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. 67309
    Prev
    Next
    INDEX
    Explanations

    forgot how to do or forgotten to do

    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
    ه
    -1.60
    er
    -1.57
     connus
    -1.47
     tournoi
    -1.45
    Theory
    -1.42
     \
    -1.42
     élevés
    -1.41
    ي
    -1.38
    ar
    -1.36
    對於
    -1.36
    POSITIVE LOGITS
     asks
    1.76
    </h1>
    1.70
     nonché
    1.59
     who
    1.52
    你也
    1.48
    </b>
    1.46
     customary
    1.45
    anız
    1.45
    малар
    1.42
     Kebijakan
    1.42
    Activations Density 0.007%

    No Known Activations