© 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. 103137
    Prev
    Next
    INDEX
    Explanations

    process completion

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

    The neuron selectively activates on numeric tokens (digits or numbers) in the text.

    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
     brutality
    -0.94
     hastily
    -0.94
     gratuitement
    -0.94
     unilaterally
    -0.91
     enorme
    -0.87
    anément
    -0.86
    大きな
    -0.85
     coarsely
    -0.85
    directly
    -0.83
    Induction
    -0.83
    POSITIVE LOGITS
     simultaneous
    1.27
     efficient
    1.23
     continued
    1.23
    による
    1.23
     successful
    1.11
    での
    1.02
     careful
    0.98
     való
    0.98
     thorough
    0.97
     systematic
    0.96
    Activations Density 0.468%

    No Known Activations