© 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. 34-GEMMASCOPE-RES-131K
    7. 75411
    Prev
    Next
    INDEX
    Explanations

    inserted parallel

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

    The neuron strongly activates on programming‐style identifiers—especially tokens containing underscores (e.g. “simple_list_item”) and similar code‐related names.

    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
     mondeo
    -0.72
     Andaman
    -0.71
     Cassel
    -0.70
     Ncert
    -0.68
    حيح
    -0.68
     SX
    -0.67
     swapping
    -0.67
    ادة
    -0.66
     acabado
    -0.66
    ajer
    -0.66
    POSITIVE LOGITS
     convoy
    0.69
     steel
    0.68
    nellement
    0.66
    の効果
    0.65
     procession
    0.65
     retention
    0.63
     Jiu
    0.63
    CCD
    0.63
     DISTRICT
    0.62
     Benoît
    0.62
    Activations Density 0.077%

    No Known Activations