© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13399
    Prev
    Next
    INDEX
    Explanations

    Stella, Mediterranean, ambient

    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
     剤
    -3.11
    AddHtmlAttribute
    -2.73
     行っ
    -2.70
    訁
    -2.55
    謌
    -2.44
     cihaz
    -2.44
    􀂃
    -2.28
     pengar
    -2.27
     många
    -2.25
     できる
    -2.25
    POSITIVE LOGITS
    .
    3.20
    鸶
    2.86
    ized
    2.61
    罴
    2.56
    </td>
    2.55
    ة
    2.41
    ൎ
    2.38
     schönes
    2.25
    ”،
    2.25
    觏
    2.22
    Activations Density 0.003%

    No Known Activations