© 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. 61200
    Prev
    Next
    INDEX
    Explanations

    script tag inclusions

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

    The main thing this neuron does is find absolute URLs (e.g. “http://…” or “https://…”) in HTML/script source 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
     a
    -1.52
     industrias
    -1.45
    s
    -1.41
     because
    -1.37
     only
    -1.35
     at
    -1.35
     เป็น
    -1.33
     interessiert
    -1.31
    เพราะ
    -1.31
     their
    -1.31
    POSITIVE LOGITS
    <bos>
    2.02
    可谓
    1.51
    ᵑ
    1.48
     بتوان
    1.46
    ♃
    1.45
    ających
    1.42
    ająca
    1.42
    Passo
    1.42
    Procedimento
    1.40
    LETIN
    1.39
    Activations Density 0.042%

    No Known Activations