© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100781
    Prev
    Next
    INDEX
    Explanations

    gift of choice, pound athlete

    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
     schnelle
    -1.35
     всегда
    -1.34
    褔
    -1.34
    **
    -1.29
     情報
    -1.28
     melaksanakan
    -1.26
     selaku
    -1.23
     menangani
    -1.23
    ・・・・・・・・
    -1.21
    Since
    -1.20
    POSITIVE LOGITS
    </h2>
    1.55
    .
    1.39
    </h4>
    1.34
    Divider
    1.33
     ovat
    1.30
    čku
    1.29
    tifkan
    1.28
    ھے
    1.27
    šče
    1.27
     at
    1.27
    Activations Density 0.080%

    No Known Activations