© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65492
    Prev
    Next
    INDEX
    Explanations

    after log or server setup

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

    The neuron primarily activates on numeric literal tokens 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_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
    riscoll
    -0.73
    ectin
    -0.73
    oreille
    -0.71
    iew
    -0.69
     kolik
    -0.67
     Battlefield
    -0.67
    otri
    -0.67
     bazen
    -0.66
    interface
    -0.66
    issent
    -0.65
    POSITIVE LOGITS
     router
    0.91
    srv
    0.90
     server
    0.89
     routes
    0.87
    роят
    0.86
     szolg
    0.85
     recovery
    0.85
    ныя
    0.82
     quit
    0.80
     srv
    0.80
    Activations Density 0.014%

    No Known Activations