© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22181
    Prev
    Next
    INDEX
    Explanations

    doctype html

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

    This neuron detects the “doctype” declaration at the start of an HTML document.

    oai_token-act-pair · o4-miniTriggered 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
    }$
    -1.74
    ztes
    -1.73
    着一个
    -1.59
     („
    -1.39
     (=
    -1.39
    了一口
    -1.38
     dommage
    -1.33
    [$
    -1.32
    了一会儿
    -1.31
    ization
    -1.25
    POSITIVE LOGITS
     and
    1.44
     in
    1.40
     with
    1.30
    </em>
    1.27
    albero
    1.26
    ingresso
    1.23
     보기
    1.23
     acestui
    1.22
     Bardzo
    1.20
    廋
    1.20
    Activations Density 0.001%

    No Known Activations