© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54223
    Prev
    Next
    INDEX
    Explanations

    artists, observation, software, D

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

    The neuron selectively fires on numeric or quantitative tokens (e.g. numbers and measurement‐style entries) 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_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
     then
    -0.83
     pás
    -0.76
     problém
    -0.75
     useState
    -0.75
    躄
    -0.73
     reti
    -0.71
     jaws
    -0.71
     Dissolve
    -0.71
     vidas
    -0.70
    いえば
    -0.70
    POSITIVE LOGITS
    lettre
    0.87
    四川
    0.84
    bonsoir
    0.81
     livello
    0.80
     metrów
    0.79
     hearty
    0.78
    ческой
    0.78
     Tämä
    0.78
    čni
    0.77
     Bạn
    0.77
    Activations Density 0.126%

    No Known Activations