© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1145
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    श्लेषण
    -1.09
     asynchronously
    -0.89
     chien
    -0.87
     médic
    -0.86
     ботинки
    -0.83
    karan
    -0.82
    卞
    -0.82
     Propiedad
    -0.82
    ाइड
    -0.82
    cioni
    -0.82
    POSITIVE LOGITS
    url
    1.16
    URLs
    1.13
     url
    1.11
    ämään
    1.03
     URLs
    1.02
    URL
    0.99
     link
    0.96
    Url
    0.93
     URL
    0.86
     hyper
    0.82
    Activations Density 0.003%

    No Known Activations