© 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. 20311
    Prev
    Next
    INDEX
    Explanations

    acp, password, title, paper, ser

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

    The neuron fires on code‐style identifiers or names containing underscores (i.e. snake_case or similar tokens).

    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
     antonio
    -1.60
    si
    -1.56
    ↵
    -1.51
     vuitton
    -1.51
    t
    -1.49
    というのも
    -1.47
     liknande
    -1.45
    man
    -1.43
    sta
    -1.43
    ac
    -1.40
    POSITIVE LOGITS
     they
    1.93
     the
    1.88
     of
    1.78
     it
    1.70
     ayudará
    1.59
    alami
    1.52
     dará
    1.50
    ⽼
    1.50
    every
    1.48
    plantilla
    1.48
    Activations Density 0.096%

    No Known Activations