© 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. 77483
    Prev
    Next
    INDEX
    Explanations

    medical infections and recommendations

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

    questions followed by common answers

    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
     অভিন
    0.50
     ክፍል
    0.50
     dateTime
    0.47
     وی
    0.45
     类型
    0.44
    μου
    0.43
     तीसरे
    0.43
     ች
    0.42
     পাবেন
    0.42
     स्वचालित
    0.41
    POSITIVE LOGITS
     recomendaciones
    0.52
    aunque
    0.52
     oste
    0.49
     obstetric
    0.48
     evidencias
    0.46
    imbledon
    0.46
     paediatric
    0.46
    empirical
    0.46
     aunque
    0.45
    infect
    0.45
    Activations Density 0.001%

    No Known Activations