© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7362
    Prev
    Next
    INDEX
    Explanations

    accounts for, track on, moon appear, German-speaking, names and, not Lies, To tell, niece,

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

    The neuron detects LinkedIn-style résumé or professional-profile phrasing—phrases listing work experience, industries, and skills.

    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
    
    0.70
    І
    0.68
    前提
    0.66
    刳
    0.65
    的一个
    0.62
     вари
    0.61
    massive
    0.60
    考虑到
    0.60
    ని
    0.59
    making
    0.59
    POSITIVE LOGITS
    ುವುದಿಲ್ಲ
    0.73
    ೆಯನ್ನು
    0.71
    ють
    0.68
     توسط
    0.67
    ISIONS
    0.66
    勉
    0.66
     خواهد
    0.64
     Cis
    0.63
     combat
    0.63
    өг
    0.62
    Activations Density 0.000%

    No Known Activations