© 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. 22-GEMMASCOPE-RES-131K
    7. 25296
    Prev
    Next
    INDEX
    Explanations

    urls starting with http or https

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

    The neuron detects web URL strings (e.g. “http://” or “https://” links).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    URLs and hyperlinks, particularly the "http://" or "https://" protocol prefix.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to web links and URL markup (http/https links and surrounding link formatting).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Lazar
    -1.00
    TableHead
    -0.90
    enggarakan
    -0.88
     spé
    -0.84
    новения
    -0.84
     kvě
    -0.84
    Autoritní
    -0.81
    depor
    -0.81
    Haute
    -0.81
     behar
    -0.81
    POSITIVE LOGITS
    ásban
    0.88
    rrh
    0.88
     Rückseite
    0.85
    긍
    0.85
     Almería
    0.85
     realme
    0.82
     obwohl
    0.81
     跳转
    0.81
    ಿ
    0.80
     facade
    0.79
    Activations Density 0.049%

    No Known Activations