© 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. 240
    Prev
    Next
    INDEX
    Explanations

    Symptoms

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

    The neuron fires strongly on words that appear as the very first word of a 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
     &
    0.55
    )['
    0.48
     etc
    0.48
     '&
    0.46
     concerto
    0.45
     nomad
    0.44
     dennoch
    0.44
     κ
    0.44
     likewise
    0.43
    ):
    0.43
    POSITIVE LOGITS
     मींस
    0.59
     means
    0.57
    というか
    0.55
    ലാണ്
    0.54
    是指
    0.54
    矢
    0.54
    不仅
    0.53
    不僅
    0.53
     znamená
    0.52
    指的是
    0.52
    Activations Density 0.032%

    No Known Activations