© 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. 90662
    Prev
    Next
    INDEX
    Explanations

    watch case, crown, lugs

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

    The neuron primarily activates on numeric tokens (digits and numbers) 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_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
    τούν
    -0.73
    lebo
    -0.72
    ölt
    -0.72
    𝑬
    -0.71
    łej
    -0.69
     PEL
    -0.69
    othermic
    -0.67
    갈
    -0.67
    장
    -0.67
     monthly
    -0.67
    POSITIVE LOGITS
     crown
    1.45
     case
    1.37
     crowns
    1.20
     Crown
    1.17
    Crown
    1.16
    crown
    1.11
    case
    0.99
    Case
    0.99
     lugs
    0.98
     screw
    0.94
    Activations Density 0.018%

    No Known Activations