© 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. 34-GEMMASCOPE-RES-131K
    7. 50480
    Prev
    Next
    INDEX
    Explanations

    static and import code keywords

    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_34/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
    ıyors
    -1.16
     cometer
    -1.14
     nélk
    -1.10
    𓆝
    -1.06
    excellents
    -1.06
    Interment
    -1.03
    껴
    -1.03
    Antworten
    -1.03
    delingen
    -1.02
     såsom
    -1.01
    POSITIVE LOGITS
    сия
    1.18
     may
    1.16
     previously
    1.00
    此外
    1.00
     latter
    0.96
    ocrats
    0.95
     earlier
    0.94
    耆
    0.94
    wigs
    0.93
     several
    0.93
    Activations Density 0.207%

    No Known Activations