© 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. 34-GEMMASCOPE-RES-131K
    7. 1300
    Prev
    Next
    INDEX
    Explanations

    software warranty disclaimer

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

    The neuron strongly activates on multi‐line comment or docstring delimiters and the large comment blocks they enclose.

    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
     beträgt
    -0.79
     típus
    -0.78
    面の
    -0.75
     EVOLUTION
    -0.74
    showthread
    -0.74
    mentaire
    -0.73
    delaide
    -0.71
    tonne
    -0.71
     STEEL
    -0.70
    ایق
    -0.70
    POSITIVE LOGITS
     Dew
    0.77
     spiro
    0.76
     Könige
    0.75
    ឧ
    0.74
    끄
    0.74
     Mays
    0.72
    ungkin
    0.72
     Genetics
    0.70
    
    0.70
    ブログ
    0.69
    Activations Density 0.001%

    No Known Activations