© 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. 7317
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

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

    The neuron chiefly fires on HTML document‐type and browser compatibility mode tokens (e.g. DOCTYPE, PUBLIC, DTD, “compatibility mode” and related terms).

    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
    тился
    -1.24
     konkrét
    -1.20
    ığında
    -1.14
    тории
    -1.13
     dôle
    -1.12
    емого
    -1.09
    씀
    -1.09
    धान
    -1.07
    kø
    -1.06
     atuais
    -1.06
    POSITIVE LOGITS
     each
    1.15
    แต่
    1.06
     seven
    1.05
    ]
    1.03
    }
    1.02
     stav
    1.02
     being
    1.02
     there
    1.01
    sedi
    1.00
    vább
    1.00
    Activations Density 0.136%

    No Known Activations