© 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. 39664
    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
     giusti
    -1.12
     inocente
    -1.10
     pasaj
    -1.10
     rychle
    -1.09
     stavu
    -1.09
    뭘
    -1.09
     Überras
    -1.06
     atento
    -1.05
     portátil
    -1.05
    secuencias
    -1.05
    POSITIVE LOGITS
     =
    1.23
    -
    1.00
     ->
    0.98
    {
    0.97
    _
    0.96
    “
    0.90
     Freitag
    0.90
    ⎪
    0.90
     Kontakt
    0.90
    ),
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.