© 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. 40076
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

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

    The neuron strongly fires on numeric tokens (integer literals) in the 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
     because
    -1.30
     if
    -1.26
     during
    -1.22
     before
    -1.11
    nın
    -1.09
     while
    -1.09
     from
    -1.06
     schmeckt
    -1.04
     on
    -1.01
     when
    -1.00
    POSITIVE LOGITS
    AppRoutingModule
    0.98
     Dinas
    0.96
     تشکر
    0.93
    hence
    0.92
     („
    0.91
     schließlich
    0.90
     asume
    0.90
    eventually
    0.89
    莇
    0.88
     этих
    0.87
    Activations Density 0.016%

    No Known Activations