© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161725
    Prev
    Next
    INDEX
    Explanations

    Census Bureau profiles

    np_acts-logits-general · gemini-2.5-flash-lite

    surprising, unexpected, or useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    搾
    0.50
     ABV
    0.50
     Relation
    0.49
     mén
    0.48
     conciencia
    0.48
    anks
    0.47
     resistencia
    0.47
     resistance
    0.46
     producción
    0.46
     resistência
    0.46
    POSITIVE LOGITS
    </th>
    0.51
    专门
    0.50
     উপ
    0.49
     solche
    0.48
    编写
    0.48
     پس
    0.47
    现场
    0.47
     بود
    0.44
    🧬
    0.44
     تامین
    0.44
    Activations Density 0.000%

    No Known Activations