© 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. 115828
    Prev
    Next
    INDEX
    Explanations

    principal end

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

    The neuron fires on numeric tokens—sequences of digits (e.g. version numbers, IDs, or other numbers).

    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
     Roc
    -0.92
    
    -0.87
     staden
    -0.74
     лента
    -0.72
    Inactive
    -0.68
    internalType
    -0.68
    ρία
    -0.66
    分け
    -0.66
     sequentially
    -0.66
     glistening
    -0.66
    POSITIVE LOGITS
     opposite
    1.09
     reference
    0.93
    refs
    0.90
     referencing
    0.88
     refer
    0.88
    reference
    0.88
     mandatory
    0.86
     references
    0.86
     containment
    0.86
    mandatory
    0.85
    Activations Density 0.039%

    No Known Activations