© 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. 61409
    Prev
    Next
    INDEX
    Explanations

    hail from

    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
     หรือ
    -2.70
     และ
    -2.63
    尐
    -2.61
    玬
    -2.58
    และ
    -2.45
    せよ
    -2.44
    しちゃ
    -2.42
    >
    -2.38
    〜。
    -2.34
    绪
    -2.34
    POSITIVE LOGITS
     the
    3.80
    {
    3.11
    )
    3.02
    e
    2.89
    ers
    2.52
    ;'
    2.48
    烀
    2.47
    ,?
    2.45
    (
    2.45
    跟
    2.36
    Activations Density 0.004%

    No Known Activations