© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60955
    Prev
    Next
    INDEX
    Explanations

    serum acute-phase proteins

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

    family relationships (like daughters, wife, family, niece, father, son).

    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
     about
    -1.72
     this
    -1.71
     also
    -1.69
     These
    -1.65
     there
    -1.63
     latter
    -1.55
     already
    -1.52
     επίσης
    -1.51
     these
    -1.50
     musíte
    -1.50
    POSITIVE LOGITS
     kurios
    1.62
     tulis
    1.49
     akut
    1.48
     bakar
    1.48
     öde
    1.45
     mengen
    1.43
     kater
    1.41
     kalender
    1.41
     izan
    1.41
     eil
    1.38
    Activations Density 0.001%

    No Known Activations