© 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. 22-GEMMASCOPE-RES-131K
    7. 26348
    Prev
    Next
    INDEX
    Explanations

    world currencies

    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_22/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
    i
    -1.80
    d
    -1.72
    N
    -1.71
    1
    -1.70
    u
    -1.63
    R
    -1.62
    m
    -1.54
    のお知らせ
    -1.54
    b
    -1.54
    K
    -1.49
    POSITIVE LOGITS
    <bos>
    1.98
    .
    1.85
    籐
    1.65
    質感
    1.59
    顎
    1.57
     Meksi
    1.55
     TÉCNICA
    1.48
    髑
    1.48
    木製
    1.48
    翌
    1.47
    Activations Density 0.004%

    No Known Activations