© 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. 50264
    Prev
    Next
    INDEX
    Explanations

    order, field, to the

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

    The neuron is detecting numeric tokens—digit strings (including years, version numbers, and other pure‐numeric or punctuation‐delimited numbers).

    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
     europé
    -0.71
     الاف
    -0.70
     dieu
    -0.69
     comprised
    -0.68
     roul
    -0.67
    Unternehmen
    -0.67
    ChatColor
    -0.66
     ascen
    -0.66
    Diweddarwch
    -0.65
    atott
    -0.65
    POSITIVE LOGITS
    nelles
    0.97
    iq
    0.84
     Ey
    0.76
     weaning
    0.75
     MSD
    0.75
    beam
    0.74
     deform
    0.74
    enital
    0.74
     CIN
    0.74
    verified
    0.74
    Activations Density 0.014%

    No Known Activations