© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3775
    Prev
    Next
    INDEX
    Explanations

    online services and platforms

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

    The neuron fires strongly on tokens that are proper names, technical product terms, or multi-digit numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    0.68
     Washington
    0.66
     M
    0.64
    Valentine
    0.64
    VIII
    0.63
     Hy
    0.63
     StringBuffer
    0.63
     intraper
    0.63
    J
    0.63
    JTextField
    0.62
    POSITIVE LOGITS
     gebruikers
    1.05
     Nutzer
    0.93
     users
    0.90
    用户
    0.89
     utenti
    0.89
    ユーザー
    0.88
     scammers
    0.88
     marketplaces
    0.87
     платфор
    0.86
    平台
    0.85
    Activations Density 2.166%

    No Known Activations