© 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. 3806
    Prev
    Next
    INDEX
    Explanations

    **for** [duration]

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

    The neuron is primarily triggered by the preposition “for.”

    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
     pentru
    0.53
     trưng
    0.53
    畀
    0.53
     budgeted
    0.51
     piedi
    0.50
    ຖ
    0.50
     для
    0.50
    箩
    0.50
     bạn
    0.49
     để
    0.49
    POSITIVE LOGITS
     некоторое
    0.70
     Quelques
    0.67
     Oleh
    0.65
     Kön
    0.63
     Alguns
    0.63
     Reasons
    0.62
     Algunos
    0.61
     Tsai
    0.61
     sebagaimana
    0.59
     Fathers
    0.59
    Activations Density 0.144%

    No Known Activations