© 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. 34-GEMMASCOPE-RES-131K
    7. 77823
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

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

    The neuron activates on numeric literals in code (e.g., integer constants).

    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
     however
    -1.09
     However
    -0.96
    return
    -0.94
     daarom
    -0.93
     umgekehrt
    -0.90
     deswegen
    -0.90
     niets
    -0.88
    Ύ
    -0.87
     return
    -0.86
    více
    -0.86
    POSITIVE LOGITS
     actif
    0.96
                            
    0.96
     malheureux
    0.95
    if
    0.95
     Avez
    0.94
     oeil
    0.93
     tatouage
    0.93
                    
    0.92
     utan
    0.92
     voci
    0.91
    Activations Density 0.011%

    No Known Activations