© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39298
    Prev
    Next
    INDEX
    Explanations

    command line arguments or code keywords

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

    The neuron is looking for slash‐delimited filesystem path tokens (e.g. Unix-style file or directory paths).

    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
    Questão
    -1.45
    ický
    -1.26
    éditeur
    -1.23
    Tudo
    -1.22
     не
    -1.20
     veritable
    -1.19
     véritables
    -1.19
    不仅
    -1.19
     erila
    -1.18
    ızı
    -1.17
    POSITIVE LOGITS
     its
    1.73
     deswegen
    1.43
     until
    1.40
     any
    1.30
    lanco
    1.27
     perché
    1.23
     because
    1.22
     unless
    1.22
     های
    1.21
    有任何
    1.21
    Activations Density 0.051%

    No Known Activations