© 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. 34-GEMMASCOPE-RES-131K
    7. 31217
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     https
    -0.79
    https
    -0.79
    orka
    -0.79
    Біографія
    -0.79
    area
    -0.79
    You
    -0.77
    counts
    -0.75
     muy
    -0.75
    size
    -0.74
     Do
    -0.74
    POSITIVE LOGITS
     Nase
    0.93
    liberty
    0.84
    Arnaud
    0.84
    Sitemap
    0.82
    нного
    0.81
     Kitchener
    0.81
    Naomi
    0.81
    Inicial
    0.80
     Hati
    0.79
    ⊄
    0.79
    Activations Density 0.023%

    No Known Activations