© 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. 68079
    Prev
    Next
    INDEX
    Explanations

    lineage and pedigree

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

    words related to genealogy, lineage, and hereditary information.

    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
    </i>
    -2.39
    </h3>
    -2.27
     in
    -1.96
    ꜆
    -1.79
    龶
    -1.77
    慊
    -1.73
    ':
    -1.73
     gewiß
    -1.71
     ";
    -1.65
    捯
    -1.63
    POSITIVE LOGITS
    ’
    2.03
     \
    1.93
     pedigree
    1.90
    q
    1.83
    x
    1.78
    翱
    1.75
    —
    1.74
    werkers
    1.73
     diki
    1.68
     deeds
    1.67
    Activations Density 0.017%

    No Known Activations