© 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. 111956
    Prev
    Next
    INDEX
    Explanations

    BILL DOHERTY, Hand in

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

    This neuron activates on text enclosed in HTML bold tags (i.e. content inside `<b>…</b>`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    HTML/markup bold formatting, especially closing </b> tags.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    HTML closing bold tags (`</b>`).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    </h3>
    -4.34
    <em>
    -4.34
    </strong>
    -3.22
    0
    -3.08
    </em>
    -3.06
    <strong>
    -2.98
    </blockquote>
    -2.63
    “
    -2.59
    In
    -2.58
    h
    -2.58
    POSITIVE LOGITS
    </b>
    4.28
    翃
    2.64
    ⢊
    2.34
     bezpeč
    2.33
    蹰
    2.33
     representan
    2.31
     建物
    2.31
    ровал
    2.23
     ofrecen
    2.23
    onate
    2.22
    Activations Density 0.001%

    No Known Activations