© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    medical or technical terms

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

    defining a skeleton of an algorithm

    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
    ởi
    0.58
    لي
    0.56
    దు
    0.54
    је
    0.54
    рата
    0.54
    فيق
    0.54
    દ
    0.54
    рам
    0.53
    дже
    0.53
    ست
    0.53
    POSITIVE LOGITS
     microarray
    0.54
     sterility
    0.51
    tests
    0.50
     gallbladder
    0.49
    isotopes
    0.48
     台
    0.47
     hypoglycemia
    0.47
     ค่า
    0.47
     annihilation
    0.47
     cancers
    0.46
    Activations Density 0.000%

    No Known Activations