© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    repurposing, evaporation

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

    This neuron fires on the final token just before a text chunk ends, marking paragraph or segment boundaries.

    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
    fek
    0.94
    cí
    0.87
    𝒸
    0.87
     sket
    0.86
    أ
    0.86
     Außerdem
    0.84
     Akar
    0.84
     осо
    0.80
     أك
    0.79
    하였다
    0.79
    POSITIVE LOGITS
    ivity
    0.79
    ist
    0.76
     '--
    0.75
    enabled
    0.74
    ism
    0.72
    ively
    0.72
    oriented
    0.71
    amplitude
    0.71
    aliases
    0.71
    starting
    0.70
    Activations Density 0.000%

    No Known Activations