© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128216
    Prev
    Next
    INDEX
    Explanations

    economic context and consequences

    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
     then
    -1.57
     çeşitli
    -1.50
    思議
    -1.49
     {}));
    -1.42
     yüksek
    -1.40
     使っ
    -1.40
    หมาย
    -1.37
    ()}>
    -1.34
    inerario
    -1.31
    ════
    -1.30
    POSITIVE LOGITS
     التطبيق
    1.52
     ощу
    1.20
     supprimer
    1.15
     enregistrer
    1.14
     and
    1.14
     المنزل
    1.13
     fermer
    1.13
     android
    1.11
     الجديدة
    1.10
    ——–
    1.10
    Activations Density 0.061%

    No Known Activations