© 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. 22-GEMMASCOPE-RES-131K
    4. 66493
    Prev
    Next
    INDEX
    Explanations

    wikipedia and research links

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

    The neuron activates on URL components—especially the forward‐slash characters in web addresses (e.g. “/” in “http://…” or “en.wikipedia.org/…”).

    oai_token-act-pair · o4-miniTriggered 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
    〜。
    -1.26
     by
    -1.20
    хами
    -1.13
    onPressed
    -1.10
     all
    -1.05
    𝚒
    -1.03
    けどね
    -1.03
     to
    -1.02
    actable
    -1.02
    return
    -1.01
    POSITIVE LOGITS
     vieill
    1.10
     extré
    1.08
    pineapple
    1.07
    ⽬
    1.06
     exceedingly
    1.06
    набор
    1.05
    取决
    1.05
    aéroport
    1.05
     входят
    1.04
     входит
    1.03
    Activations Density 0.014%

    No Known Activations