© 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. 8728
    Prev
    Next
    INDEX
    Explanations

    well followed by punctuation or phrase

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

    the neuron is spotting sentence-initial discourse markers or filler words (e.g. “Well,” “Anyway,” etc.).

    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
    y
    1.22
    et
    1.09
    e
    1.07
    ي
    0.98
    ação
    0.95
    AN
    0.93
    reciate
    0.89
    esque
    0.87
    a
    0.87
    AL
    0.85
    POSITIVE LOGITS
     Поскольку
    0.93
    behaved
    0.89
     Один
    0.89
    しゃれ
    0.89
    覀
    0.89
     appunto
    0.87
    䍘
    0.86
     darn
    0.85
    റുക
    0.85
    िवा
    0.84
    Activations Density 0.174%

    No Known Activations