© 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. 47808
    Prev
    Next
    INDEX
    Explanations

    people categorized by role

    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
     but
    -1.41
     Füßen
    -1.38
     если
    -1.33
    </strong>
    -1.29
    ︰
    -1.27
    zzet
    -1.26
    rewsbury
    -1.23
    ༅
    -1.23
    ﹕
    -1.23
     ANOTHER
    -1.20
    POSITIVE LOGITS
     usado
    1.43
     zarówno
    1.40
     choice
    1.32
    2
    1.24
    </td>
    1.16
    帰る
    1.16
     taką
    1.16
     plana
    1.14
     miniatur
    1.14
     utilizada
    1.13
    Activations Density 0.035%

    No Known Activations