© 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. 47666
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

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

    The neuron fires strongly on the main body prose (the title and the first narrative sentences) and remains silent on metadata headers, questions, and 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
     at
    -1.02
     or
    -0.98
     on
    -0.93
     graph
    -0.92
     every
    -0.88
     by
    -0.87
     +
    -0.86
    将军
    -0.86
    メートル
    -0.84
     before
    -0.83
    POSITIVE LOGITS
    IEEE
    1.22
    Rispondi
    1.12
    andering
    1.03
     galley
    0.97
     متعل
    0.96
    }}]{
    0.96
     soluzioni
    0.94
    olá
    0.94
    EVER
    0.94
     oggetti
    0.94
    Activations Density 0.016%

    No Known Activations