© 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. 22-GEMMASCOPE-RES-131K
    7. 36508
    Prev
    Next
    INDEX
    Explanations

    emotional discomfort

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

    The neuron strongly activates on multi‐digit numeric tokens (especially the hour/minute numbers and separators in timestamps or date/time stamps).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    wyżs
    -1.11
     évé
    -1.08
    жными
    -1.05
     detalj
    -1.03
    Create
    -1.03
     russa
    -1.02
    alé
    -1.02
     immobilier
    -1.02
    Actually
    -0.98
    Creating
    -0.97
    POSITIVE LOGITS
    enie
    1.08
    ratory
    0.89
    arity
    0.89
     soon
    0.86
    prises
    0.84
     S
    0.84
    fillment
    0.83
    passed
    0.82
    ingham
    0.81
     prodigy
    0.81
    Activations Density 0.000%

    No Known Activations