© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4404
    Prev
    Next
    INDEX
    Explanations

    survival and hardship

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

    The neuron strongly activates on relative‐clause descriptions of impressive personal or group achievements or origins (e.g. “who sailed around the world alone…” or “that was born in Memphis…”).

    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
     আপাতত
    1.17
     attualmente
    1.00
     estará
    0.94
     தற்போது
    0.92
     Djokovic
    0.89
     olacaktır
    0.89
     Arteta
    0.88
     sedang
    0.88
     PSOE
    0.87
     indulgent
    0.87
    POSITIVE LOGITS
     damals
    0.99
    当时
    0.87
    當時
    0.82
    当时的
    0.79
    那时候
    0.77
     तत्कालीन
    0.76
     pioneering
    0.75
    那时
    0.75
     homestead
    0.75
    当時の
    0.73
    Activations Density 0.159%

    No Known Activations