© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61254
    Prev
    Next
    INDEX
    Explanations

    HTML and code attributes

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

    This neuron responds to numeric values, especially digits in attribute assignments (e.g. numbers in HTML/XML attributes).

    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
    ℣
    -2.14
    0
    -2.11
    ᎒
    -2.08
    ጴ
    -2.06
    providedIn
    -2.06
     Each
    -1.97
     Both
    -1.95
     After
    -1.95
     جيدة
    -1.93
    sibilité
    -1.92
    POSITIVE LOGITS
    ↵
    2.50
    ’
    2.45
     protože
    2.27
    </h3>
    2.23
     continúas
    2.13
    "]();
    2.02
    "
    2.00
    を使用
    1.98
     —
    1.95
     andere
    1.94
    Activations Density 0.022%

    No Known Activations