© 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. 8785
    Prev
    Next
    INDEX
    Explanations

    Lyme disease, Freud, Fourier Transform, dA

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

    references to diseases, medical conditions, and people with medical conditions.

    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
    茕
    -3.22
    </strong>
    -2.84
    !”
    -2.70
    ൎ
    -2.63
     yelek
    -2.53
    𓋼
    -2.45
    M
    -2.38
    只剩
    -2.38
    地说
    -2.33
    歘
    -2.28
    POSITIVE LOGITS
    ’
    3.03
     were
    2.69
     In
    2.56
    ，「
    2.44
    ющие
    2.44
    ↵↵
    2.39
     dasarnya
    2.34
     '
    2.28
     You
    2.28
    </td>
    2.27
    Activations Density 0.022%

    No Known Activations