© 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. 65379
    Prev
    Next
    INDEX
    Explanations

    Indicating capability or possibility

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

    This neuron fires on relatively rare or specialized content tokens—uncommon words, technical names, or non-English terms.

    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
     عزی
    -2.64
    3
    -2.31
    ową
    -2.27
     −
    -2.25
    ated
    -2.23
    a
    -2.22
    ian
    -2.19
    8
    -2.17
    er
    -2.17
    ised
    -2.16
    POSITIVE LOGITS
    廰
    2.56
    ്ട
    2.50
     regiones
    2.17
     sichere
    2.11
     realizzato
    2.11
    chengladbach
    2.09
     可以
    2.08
    γωγ
    2.08
     nächste
    2.06
     sánh
    2.06
    Activations Density 0.001%

    No Known Activations