© 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. 10-GEMMASCOPE-RES-131K
    7. 19356
    Prev
    Next
    INDEX
    Explanations

    · symbol followed by units or identifiers

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

    The neuron fires on the interpunct “·” character (the mid‐dot used in numeric units and chemical/formula notation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     borsa
    -1.98
     gomma
    -1.84
    」、「
    -1.83
     proveniente
    -1.73
     tuta
    -1.70
     confezione
    -1.65
    </h3>
    -1.62
    」、
    -1.61
    猡
    -1.58
     multiuso
    -1.55
    POSITIVE LOGITS
    r
    2.16
    的心情
    1.98
     pero
    1.91
    訁
    1.85
    ௗ
    1.80
    Tetapi
    1.80
    你也
    1.79
     *,
    1.77
    -
    1.75
    沨
    1.75
    Activations Density 0.009%

    No Known Activations