© 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. 33712
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific titles

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

    The neuron fires on numeric tokens (especially multi-digit numbers) representing quantities or measurements.

    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
     fundamento
    -0.82
     Paroles
    -0.81
    モチ
    -0.78
    provincia
    -0.77
    parate
    -0.77
     نار
    -0.77
     тихо
    -0.76
     carport
    -0.75
    驍
    -0.73
    חס
    -0.73
    POSITIVE LOGITS
    更新
    0.89
     subsequ
    0.84
     humidifier
    0.82
     ドラマ
    0.82
    Finished
    0.81
     spindles
    0.81
    juelas
    0.80
     Finished
    0.80
     spind
    0.78
     upper
    0.76
    Activations Density 0.010%

    No Known Activations