© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43095
    Prev
    Next
    INDEX
    Explanations

    California legal citations and 'Candidatus' names

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

    country or location codes in legal citations and documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    比如
    -2.19
     '
    -2.11
     \#
    -1.88
     zeigten
    -1.87
     để
    -1.87
     terminó
    -1.84
     réalisés
    -1.82
     $^{\
    -1.81
    Lü
    -1.81
    或者
    -1.76
    POSITIVE LOGITS
     you
    1.85
    讴
    1.76
    Other
    1.74
    upuk
    1.70
     любой
    1.70
     outras
    1.70
     الجمعة
    1.66
     It
    1.65
    しないと
    1.62
     recognize
    1.61
    Activations Density 0.055%

    No Known Activations