© 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. 34-GEMMASCOPE-RES-131K
    4. 84556
    Prev
    Next
    INDEX
    Explanations

    programming code structure

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

    The neuron fires on long runs of whitespace (indentation) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     telefonu
    -1.27
    rieben
    -1.22
     triko
    -1.22
    Garonne
    -1.20
     salonu
    -1.16
     Moyen
    -1.16
     gangen
    -1.16
    unción
    -1.15
     novelas
    -1.14
     menonton
    -1.14
    POSITIVE LOGITS
    if
    1.43
    6
    1.20
    "
    1.14
    で
    1.14
    *
    1.12
    //
    1.09
    +
    1.08
     into
    1.07
     if
    1.06
    -
    1.03
    Activations Density 0.019%

    No Known Activations