© 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. 63598
    Prev
    Next
    INDEX
    Explanations

    constructor parameters and types

    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
     these
    -0.89
     near
    -0.85
    łeś
    -0.82
     finally
    -0.79
     each
    -0.77
     eventually
    -0.76
    套装
    -0.75
     usually
    -0.75
     nearly
    -0.74
     slowly
    -0.73
    POSITIVE LOGITS
     jeszcze
    1.05
     еще
    1.02
     ainda
    1.00
    ötz
    0.96
     rus
    0.96
     још
    0.95
    ्ला
    0.95
    ⁣
    0.92
    )$.
    0.91
     še
    0.91
    Activations Density 0.002%

    No Known Activations