© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79796
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.20
     because
    -1.15
    with
    -1.09
     not
    -1.08
     ў
    -1.04
     for
    -1.00
     bello
    -1.00
     municipio
    -0.99
     siihen
    -0.96
    国家
    -0.96
    POSITIVE LOGITS
     disminu
    1.30
     différentes
    1.25
     iria
    1.20
     caiu
    1.18
     différents
    1.18
    ¹.
    1.16
    élimin
    1.16
     trouxe
    1.15
    Procedimento
    1.13
    ౦
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.