© 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. 8291
    Prev
    Next
    INDEX
    Explanations

    conditions met

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

    This neuron detects the instructional phrase “if applicable,” flagging when a conditional, optional instruction is introduced.

    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
     if
    -1.27
     fár
    -1.15
     chaleco
    -1.13
     that
    -1.08
     surtido
    -1.05
    いざ
    -1.05
     bocetos
    -1.03
    
    -1.03
     wenn
    -0.99
     דער
    -0.99
    POSITIVE LOGITS
     or
    1.16
     yaitu
    0.96
    itola
    0.92
     según
    0.92
     додат
    0.91
     конечно
    0.88
    Most
    0.87
     Throughout
    0.86
     While
    0.86
     provide
    0.85
    Activations Density 0.046%

    No Known Activations