© 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. 108128
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

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

    The neuron is triggered by tokens that are uppercase identifiers or type/class names (i.e. words starting with a capital letter).

    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
    матика
    -0.90
     blik
    -0.87
    hã
    -0.87
     foglie
    -0.86
    ногда
    -0.86
    如果你
    -0.83
    amatan
    -0.82
     papir
    -0.82
     nothing
    -0.82
    ñas
    -0.82
    POSITIVE LOGITS
    
    0.80
     MOU
    0.79
    urata
    0.78
    נים
    0.76
     dezelfde
    0.73
     affix
    0.73
    titudine
    0.73
     ceux
    0.71
     verheiratet
    0.71
     mehrere
    0.70
    Activations Density 0.102%

    No Known Activations