© 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. 11133
    Prev
    Next
    INDEX
    Explanations

    affecting its

    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
    </i>
    -2.56
     '
    -2.25
    นี้
    -2.20
    GRAFÍA
    -2.14
     huéspedes
    -2.14
    UCIÓN
    -2.13
     so
    -2.03
    嵙
    -2.03
     perí
    -2.03
     have
    -1.98
    POSITIVE LOGITS
    ↵
    3.19
    肫
    2.83
     }
    2.73
     voor
    2.61
    for
    2.52
    </em>
    2.48
     you
    2.44
    搋
    2.31
    anc
    2.27
    柃
    2.27
    Activations Density 0.015%

    No Known Activations