© 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. 78785
    Prev
    Next
    INDEX
    Explanations

    court dates

    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
     nghệ
    -0.76
    mity
    -0.76
     توا
    -0.74
    Zhou
    -0.73
    groupby
    -0.72
    tieth
    -0.72
    ``,
    -0.72
    ikin
    -0.71
    qas
    -0.71
    над
    -0.71
    POSITIVE LOGITS
     Almost
    0.80
     almost
    0.76
     without
    0.75
    த
    0.71
    先日
    0.71
     amidst
    0.71
     серед
    0.70
     Without
    0.70
    pato
    0.69
     really
    0.69
    Activations Density 0.027%

    No Known Activations