© 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. 75193
    Prev
    Next
    INDEX
    Explanations

    location separators

    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
     poivre
    -1.98
    ном
    -1.98
    </strong>
    -1.78
    という感じ
    -1.78
    </h3>
    -1.77
    \
    -1.75
     pharmacie
    -1.70
    ть
    -1.70
     maroca
    -1.63
     médic
    -1.61
    POSITIVE LOGITS
     these
    2.55
     now
    2.17
     you
    2.05
    ogens
    1.95
     ahora
    1.92
    䊐
    1.91
     setiap
    1.91
     jetzt
    1.85
     here
    1.83
    是以
    1.82
    Activations Density 0.005%

    No Known Activations