© 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. 44819
    Prev
    Next
    INDEX
    Explanations

    sacroiliac diagnostics

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

    parts of taxonomic or scientific names ending with "ili".

    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
    龊
    -2.88
    陛下
    -2.56
    .
    -2.52
    担任
    -2.50
     From
    -2.48
    In
    -2.45
     penchant
    -2.44
     Recent
    -2.44
     le
    -2.41
    四年
    -2.39
    POSITIVE LOGITS
    </sub>
    3.13
    </h3>
    2.86
    ili
    2.83
    栳
    2.63
    l
    2.63
    豋
    2.63
    茕
    2.58
    )("
    2.34
    s
    2.34
    ?’
    2.33
    Activations Density 0.017%

    No Known Activations