© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    struggling with / pursue

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

    The neuron primarily fires on the first content word of a new segment or sentence.

    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
     registrada
    0.86
    ﯽ
    0.84
    সম্পাদকীয়
    0.82
     enregistré
    0.82
    נג
    0.81
    愪
    0.79
     společnosti
    0.78
    們
    0.77
     সমালো
    0.75
     grupy
    0.75
    POSITIVE LOGITS
    stoke
    0.79
    onden
    0.72
    eda
    0.71
    eig
    0.68
     விட்ட
    0.68
    drag
    0.67
    dock
    0.67
    oak
    0.66
    atten
    0.66
    edi
    0.65
    Activations Density 0.005%

    No Known Activations