© 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. 22-GEMMASCOPE-RES-131K
    7. 117
    Prev
    Next
    INDEX
    Explanations

    identification and restaurants

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

    The neuron specializes in spotting file‐input operations and path or filename tokens (e.g. file paths, “ReadFile,” “ioutil,” “.txt”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     if
    -0.98
     speł
    -0.96
    พาะ
    -0.95
     zapach
    -0.91
    壓力
    -0.89
     merece
    -0.88
     самых
    -0.88
    ogues
    -0.88
     zentralen
    -0.86
     surfers
    -0.85
    POSITIVE LOGITS
     tanong
    1.20
     pét
    1.10
     saveurs
    1.09
    vetrain
    1.08
    瘻
    1.05
    痰
    1.01
     applau
    0.97
    大家的
    0.96
    replaceAll
    0.95
    damento
    0.95
    Activations Density 0.006%

    No Known Activations