© 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. 98840
    Prev
    Next
    INDEX
    Explanations

    crimes and hardships listed after "including(,)"

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

    The neuron strongly activates on numeric tokens—particularly multi‐digit numbers used as statistics or counts.

    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
     wickedness
    -1.12
     ترب
    -1.02
     wretch
    -0.98
     Proble
    -0.92
     kejadian
    -0.90
     heapq
    -0.90
     problema
    -0.89
     perpetrators
    -0.88
     iniquity
    -0.87
    素晴
    -0.87
    POSITIVE LOGITS
     murder
    1.35
    (!_
    1.21
     disease
    1.10
     forced
    1.10
     poverty
    1.08
    itaal
    1.06
     hunger
    1.03
     drug
    1.03
     war
    1.02
     racial
    0.98
    Activations Density 0.054%

    No Known Activations