© 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. 10-GEMMASCOPE-RES-131K
    7. 57
    Prev
    Next
    INDEX
    Explanations

    race, racemic, track, calendar

    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_10/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
    を始め
    -2.67
    最后由
    -2.52
     conceptually
    -2.50
    眼下
    -2.45
    已经有
    -2.39
    每一次
    -2.36
    还是要
    -2.33
    旰
    -2.33
    </h2>
    -2.31
    聼
    -2.30
    POSITIVE LOGITS
    o
    3.83
    e
    3.55
    i
    2.91
     wee
    2.61
    ⩩
    2.56
    NÍ
    2.45
     några
    2.41
    𝕿
    2.36
    a
    2.34
     leur
    2.31
    Activations Density 0.014%

    No Known Activations