© 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. 128255
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     to
    -2.17
     on
    -2.11
    不同
    -2.03
     for
    -1.89
    </i>
    -1.81
     of
    -1.61
     ricerche
    -1.59
    -1.53
     Also
    -1.52
    {~
    -1.52
    POSITIVE LOGITS
    ynchronously
    1.61
     compradores
    1.60
    勿論
    1.55
     作る
    1.49
     compañeros
    1.44
     madres
    1.41
     MaterialApp
    1.40
    ᱽ
    1.38
    紆
    1.38
    ़
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.