© 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. 75181
    Prev
    Next
    INDEX
    Explanations

    holmes and sherlock

    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
     acknowledgment
    -2.47
     aventure
    -2.45
     impetus
    -2.41
     outrage
    -2.31
    犄
    -2.27
     That
    -2.23
    ஂ
    -2.22
     aching
    -2.20
    ࿚
    -2.20
    section
    -2.19
    POSITIVE LOGITS
    圌
    3.48
    to
    3.41
    轳
    2.81
    所以我
    2.55
     dieß
    2.48
    <bos>
    2.47
    雠
    2.42
    かげ
    2.39
    我只是
    2.34
    ܞ
    2.31
    Activations Density 0.003%

    No Known Activations