© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118281
    Prev
    Next
    INDEX
    Explanations

    court, wall, for

    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
    拼
    -0.72
    Aa
    -0.70
    бы
    -0.70
    ioc
    -0.65
    TEN
    -0.65
     Lotto
    -0.65
    よ
    -0.65
    with
    -0.64
     ten
    -0.63
    А
    -0.62
    POSITIVE LOGITS
    methyl
    0.91
    մ
    0.83
    ⣿
    0.82
    მ
    0.77
    म
    0.77
    mender
    0.74
     Điện
    0.73
    methy
    0.71
    َم
    0.71
     Krishna
    0.70
    Activations Density 0.395%

    No Known Activations