© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37804
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, and semicolons

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

    The neuron strongly activates on sentence-final full stops (periods).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -3.28
    <h2>
    -1.43
    ).\\
    -1.20
     ecco
    -1.15
    ."
    -1.13
    」。
    -1.12
    》。
    -1.12
    ”。
    -1.10
    )!
    -1.10
    Below
    -1.09
    POSITIVE LOGITS
    Sklici
    0.98
     forklar
    0.93
    同时也
    0.90
    ﹔
    0.89
    ému
    0.89
     réception
    0.89
     стаття
    0.88
    ;</
    0.88
     ด้วย
    0.88
    𝑟
    0.88
    Activations Density 0.049%

    No Known Activations