© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38685
    Prev
    Next
    INDEX
    Explanations

    online platforms and crowdfunding

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

    This neuron detects mentions of online platforms and services (e.g. Patreon, Kickstarter, Mega, Discord, Twitch, Steam).

    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
    7
    -2.34
    4
    -2.30
    1
    -2.09
    2
    -2.06
    いえば
    -1.98
    if
    -1.91
    
    -1.91
    3
    -1.86
    8
    -1.83
     reconocida
    -1.77
    POSITIVE LOGITS
    '
    2.17
    ↵
    1.77
    Ⅰ
    1.70
    在庫
    1.64
     Enero
    1.63
    🐱
    1.55
     など
    1.53
     Viena
    1.51
     agujeros
    1.51
     chargé
    1.50
    Activations Density 0.005%

    No Known Activations