© 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. 100587
    Prev
    Next
    INDEX
    Explanations

    notch, line, jump, pathway, proteins

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

    The neuron primarily detects mentions of "Notch" and related signaling proteins in biological or technical contexts.

    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
    殒
    -2.31
    安裝
    -2.22
    目次
    -2.19
    ቭ
    -2.17
     ferrovia
    -2.16
    쫀
    -2.13
     RSITY
    -2.11
    极了
    -2.08
     Onze
    -2.05
    兵庫
    -2.03
    POSITIVE LOGITS
    '
    4.09
    </b>
    4.06
    s
    3.13
     наиболее
    2.56
    </td>
    2.41
    ೢ
    2.34
    ).
    2.25
    </h5>
    2.20
     глав
    2.19
    &#
    2.17
    Activations Density 0.002%

    No Known Activations