© 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. 22-GEMMASCOPE-RES-131K
    7. 73932
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

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

    The neuron fires on anatomical directional prefixes (e.g. “antero–”) indicating spatial orientation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    っぱり
    -1.09
    子は
    -1.03
    かね
    -1.00
    Makanan
    -0.98
     нашего
    -0.97
    johtaja
    -0.97
     нашей
    -0.96
    こんなに
    -0.95
     examples
    -0.95
    elegante
    -0.94
    POSITIVE LOGITS
     u
    0.96
    अ
    0.94
    de
    0.94
     sigo
    0.92
    </code>
    0.91
    Ḥ
    0.91
     En
    0.90
    Ḳ
    0.89
     य
    0.88
     In
    0.85
    Activations Density 0.101%

    No Known Activations