© 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. 106723
    Prev
    Next
    INDEX
    Explanations

    titles and named entities

    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
     dezelfde
    -0.98
    だったので
    -0.97
    henge
    -0.97
    cartier
    -0.96
     Frases
    -0.93
     Tér
    -0.93
    ција
    -0.93
    蚜
    -0.92
    urangi
    -0.90
    elcome
    -0.88
    POSITIVE LOGITS
     That
    1.05
     factor
    0.99
     &
    0.96
    ᴥ
    0.95
     (
    0.95
    </b>
    0.94
     Very
    0.93
     before
    0.93
    !!
    0.88
     we
    0.88
    Activations Density 0.067%

    No Known Activations