© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34866
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

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

    The neuron fires on user‐defined identifier tokens—especially parameter and variable names 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_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
     already
    -1.02
     đị
    -0.97
     konden
    -0.94
     prezenta
    -0.90
    GRect
    -0.89
    nemers
    -0.89
    IFYING
    -0.86
    Recher
    -0.85
     уже
    -0.84
     animada
    -0.84
    POSITIVE LOGITS
     without
    0.88
     による
    0.86
    тиков
    0.84
     porém
    0.84
     prosa
    0.82
     Thos
    0.77
    शु
    0.75
     Buys
    0.74
    nswer
    0.73
    却是
    0.73
    Activations Density 0.002%

    No Known Activations