© 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. 7621
    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
    0
    -0.98
    하며
    -0.92
     easterly
    -0.87
    aj
    -0.87
    садка
    -0.86
    pi
    -0.84
    s
    -0.84
     CHF
    -0.83
     thankful
    -0.82
     francs
    -0.82
    POSITIVE LOGITS
    ouvrir
    0.93
    orszá
    0.92
    дото
    0.91
    argento
    0.90
     aguj
    0.90
     samym
    0.88
     señaló
    0.88
    kým
    0.87
     installé
    0.87
     molte
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.