© 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. 219616
    Prev
    Next
    INDEX
    Explanations

    illness, pregnancy, resilience

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

    origin or basis of concepts

    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
    ק
    0.50
    ин
    0.49
    י
    0.46
    น
    0.46
    helloworld
    0.46
    มัน
    0.45
    स्कृत
    0.44
    luc
    0.44
    ზ
    0.44
    Iranian
    0.43
    POSITIVE LOGITS
     enfermedades
    0.51
     BOTH
    0.50
    BOTH
    0.49
     keseluruhan
    0.48
     Pregnancy
    0.48
     pregnancies
    0.47
     erneut
    0.47
     premature
    0.44
     arterios
    0.44
     illness
    0.44
    Activations Density 0.001%

    No Known Activations