© 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. 238003
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
     financially
    0.49
     अच्छा
    0.48
     अच्छी
    0.48
     aggressively
    0.46
     বিপ
    0.45
     ज्यादा
    0.44
     sponsored
    0.44
    勢
    0.42
    襬
    0.42
    克
    0.41
    POSITIVE LOGITS
     podstawie
    0.48
    zięki
    0.48
     erinner
    0.47
    ewöhn
    0.47
     людини
    0.46
     treści
    0.45
    ależy
    0.45
     ervaring
    0.45
     doświad
    0.44
     roślin
    0.44
    Activations Density 0.001%

    No Known Activations