© 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. 34-GEMMASCOPE-RES-131K
    4. 115613
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "in the" or "in"

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

    The neuron primarily activates on numeric tokens—especially four‐digit numbers like years or other numeric codes.

    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
     pæ
    -0.88
    Aç
    -0.85
    ouncy
    -0.85
     sophisticated
    -0.82
    הע
    -0.81
    手伝
    -0.81
    代价
    -0.80
     kleines
    -0.79
     dlaczego
    -0.77
     passato
    -0.77
    POSITIVE LOGITS
     הער
    0.88
     بازیگر
    0.88
    Cite
    0.88
    tille
    0.87
     awk
    0.85
     armes
    0.83
    iol
    0.82
    npy
    0.82
    ;;;;
    0.81
    /////
    0.81
    Activations Density 0.056%

    No Known Activations