© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25472
    Prev
    Next
    INDEX
    Explanations

    programming code and data structures

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

    The neuron fires on tokens that look like code identifiers (e.g. variable or macro names such as CSS prefixes or C‐macro identifiers).

    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
    อร
    -0.92
    while
    -0.92
     Mitteln
    -0.90
    self
    -0.89
     −
    -0.88
     composés
    -0.88
     undersø
    -0.85
     damal
    -0.85
    cutaneous
    -0.84
     pagrind
    -0.84
    POSITIVE LOGITS
     livré
    1.03
     préparé
    1.02
     Ná
    0.99
     monté
    0.96
    ressible
    0.93
    Feuer
    0.93
     touché
    0.93
    极其
    0.91
     sœurs
    0.91
    資産
    0.90
    Activations Density 0.002%

    No Known Activations