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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110550
    Prev
    Next
    INDEX
    Explanations

    HTML manipulation and insertion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     text
    -1.29
    text
    -1.19
     texts
    -1.08
    getText
    -0.95
     Text
    -0.95
     <
    -0.90
    Texts
    -0.90
     getText
    -0.89
    Text
    -0.88
    文本
    -0.82
    POSITIVE LOGITS
    innerHTML
    1.75
     inner
    1.23
     HTML
    0.98
    html
    0.98
    Inner
    0.94
    inner
    0.89
     Inner
    0.89
     vnitř
    0.85
     INNER
    0.84
    interno
    0.82
    Activations Density 0.015%

    No Known Activations