© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8544
    Prev
    Next
    INDEX
    Explanations

    defining relationships between concepts

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

    The neuron fires on uncommon, technical or domain‐specific words (e.g. “inhalation,” “forecasts,” “transport,” “relieve,” “Germany”), effectively detecting specialized terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sentiment
    0.74
    }\
    0.73
    agriculture
    0.70
    aan
    0.70
    about
    0.69
    بانی
    0.68
    atisme
    0.67
    President
    0.66
    sad
    0.66
    سال
    0.65
    POSITIVE LOGITS
     ponytail
    0.97
     пары
    0.91
     ομά
    0.88
     eukaryotic
    0.86
     rhenium
    0.84
     CpG
    0.84
     камеры
    0.81
     xaxis
    0.80
     polyurethane
    0.80
     câmera
    0.80
    Activations Density 0.000%

    No Known Activations