© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    takeaway, microsomes, microsurgery

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

    scientific terms related to cellular structures, particularly "microsomes" and similar biochemical 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
     The
    -3.64
    </i>
    -3.34
     —
    -2.91
     This
    -2.67
    </b>
    -2.67
    </u>
    -2.59
    是
    -2.53
     pero
    -2.52
     avec
    -2.48
    ;
    -2.47
    POSITIVE LOGITS
    नलोड
    2.91
    玗
    2.70
    ᯾
    2.50
    礽
    2.47
    ᯅ
    2.45
    尨
    2.41
    酲
    2.38
    Ꙭ
    2.34
    鰱
    2.34
    atrician
    2.34
    Activations Density 0.004%

    No Known Activations