© 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. 14534
    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
     in
    -1.98
    up
    -1.61
    ta
    -1.49
     because
    -1.48
     or
    -1.48
    b
    -1.45
     from
    -1.45
    n
    -1.44
    {
    -1.39
    \
    -1.38
    POSITIVE LOGITS
    鞮
    1.51
     penser
    1.48
     teneur
    1.45
     jouet
    1.42
    igre
    1.42
     Anexo
    1.41
    Α
    1.38
    ANCHE
    1.35
     Ensino
    1.35
    木材
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.