© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    fear of pain

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

    The neuron strongly activates on explicit numeric tokens and technical identifiers (e.g. ages, days, verse/chapter numbers, ligand or model codes, auction step numbers) anywhere in the text.

    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
     경영
    0.76
     overarching
    0.75
     कपकेक
    0.75
     sprawling
    0.72
    რულ
    0.71
    PhysRev
    0.71
    
    0.70
     곧
    0.70
    ⾏
    0.69
     burgeoning
    0.69
    POSITIVE LOGITS
     notific
    0.72
     zabezpie
    0.72
     detector
    0.71
     alot
    0.67
     hade
    0.67
     notification
    0.66
     courrier
    0.66
     fece
    0.66
     elettron
    0.65
     recieved
    0.65
    Activations Density 1.046%

    No Known Activations