© 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. 19346
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and labels

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

    The neuron fires on programming‐style identifiers—i.e. tokens that are names of modules, files, functions, or other code symbols.

    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
     alrededores
    -1.97
     it
    -1.65
     jueces
    -1.62
     diputados
    -1.45
     amid
    -1.42
    *{-
    -1.41
    みたいに
    -1.39
     juzg
    -1.37
     merkez
    -1.37
     chiusura
    -1.35
    POSITIVE LOGITS
    They
    2.05
     Sometimes
    1.56
    Some
    1.49
    when
    1.48
     Some
    1.42
     anta
    1.40
     Many
    1.40
    what
    1.39
     kuti
    1.39
     When
    1.33
    Activations Density 0.098%

    No Known Activations