© 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. 39914
    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
    女
    -1.09
    𝓿
    -1.02
     ugy
    -1.00
    szám
    -1.00
     dámské
    -1.00
     magát
    -0.98
     Artículos
    -0.98
     wherein
    -0.98
     瘦
    -0.96
    苌
    -0.96
    POSITIVE LOGITS
    e
    0.98
    Also
    0.97
     developments
    0.93
     поднима
    0.80
     ужа
    0.80
     to
    0.80
     changes
    0.79
     pater
    0.79
     arbeitet
    0.79
     тоже
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.