© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84027
    Prev
    Next
    INDEX
    Explanations

    http(s):// URLs detected

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

    The neuron is primarily triggered by URL components (e.g. “http,” “https,” “://”) and thus detects the presence of web links.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     هنا
    -0.83
    spiller
    -0.77
     flo
    -0.72
     Մ
    -0.71
    mais
    -0.71
     bon
    -0.71
     న
    -0.70
     لهم
    -0.70
    CAPTCHA
    -0.70
    телите
    -0.70
    POSITIVE LOGITS
     malen
    0.87
     vía
    0.78
    选
    0.78
    via
    0.77
    ƚ
    0.74
    ervative
    0.74
    eles
    0.73
     escolher
    0.73
    ական
    0.73
    conform
    0.73
    Activations Density 0.018%

    No Known Activations