© 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. 84017
    Prev
    Next
    INDEX
    Explanations

    ticket purchase links

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

    The neuron selectively activates on domain‐name and URL fragments (e.g. “splashthat.com,” “goo.gl,” “carpediem.cd,” etc.), effectively spotting web addresses.

    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
     оружия
    -1.24
    Referințe
    -1.23
    <b>
    -1.21
     even
    -1.18
    \
    -1.16
    诟
    -1.16
     avião
    -1.14
    ,
    -1.13
     both
    -1.12
     keramik
    -1.11
    POSITIVE LOGITS
    ญี่ป
    1.48
    tión
    1.42
    ﻷ
    1.38
     detalló
    1.38
    ГЛА
    1.36
    ﻹ
    1.30
     السياس
    1.30
    bihi
    1.29
     memudahkan
    1.29
    czki
    1.28
    Activations Density 0.010%

    No Known Activations