© 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. 66604
    Prev
    Next
    INDEX
    Explanations

    T lymphocytes

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

    technical scientific notation including symbols like + and - that appear in chemical formulas, mathematical expressions, and specialized scientific terms.

    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
    mathrm
    -1.80
    Also
    -1.55
    m
    -1.48
    is
    -1.46
    ar
    -1.40
    他不
    -1.36
    Before
    -1.35
    Not
    -1.34
     ?
    -1.32
     cristiana
    -1.31
    POSITIVE LOGITS
     efficaces
    1.49
     utilisés
    1.36
     someplace
    1.30
     comparação
    1.29
     —
    1.29
     nová
    1.27
    therners
    1.27
     semblables
    1.26
     entró
    1.24
     mécanisme
    1.24
    Activations Density 0.103%

    No Known Activations