© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99363
    Prev
    Next
    INDEX
    Explanations

    illness, treatment, and recovery

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

    terms related to medical and health support services, including therapy, treatment, recovery, and patient care.

    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
     to
    -2.20
     of
    -1.85
     was
    -1.37
    >(</
    -1.15
    性を
    -1.15
    z
    -1.14
    longrightarrow
    -1.12
    la
    -1.09
    not
    -1.09
    还是
    -1.07
    POSITIVE LOGITS
     atractiva
    1.76
     három
    1.38
     atractivo
    1.37
     almofada
    1.37
    lisi
    1.35
    Ꮚ
    1.33
     kanad
    1.32
     cuerdas
    1.29
     emisiones
    1.28
     bicicletas
    1.27
    Activations Density 0.266%

    No Known Activations