© 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. 22455
    Prev
    Next
    INDEX
    Explanations

    biotinylated proteins

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

    The neuron recognizes biotin and biotinylation references in scientific text.

    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
    ↵↵
    -3.42
      
    -2.47
    </strong>
    -2.44
    <i>
    -2.30
     
    -2.25
     engaging
    -2.20
    <td>
    -2.19
    д
    -2.17
     —
    -2.11
    </h1>
    -2.08
    POSITIVE LOGITS
    也沒
    2.69
    為何
    2.63
     intende
    2.58
    都沒
    2.55
    幾乎
    2.47
    鼉
    2.44
    なー
    2.42
    壟
    2.41
    ごち
    2.36
    ・・・」
    2.36
    Activations Density 0.001%

    No Known Activations