© 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. 98208
    Prev
    Next
    INDEX
    Explanations

    20th century periods

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

    The neuron detects numeric tokens—especially multi‐digit numbers such as years.

    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
    ங்கு
    -0.85
     نوجوان
    -0.82
     bevor
    -0.79
    endale
    -0.74
     statue
    -0.73
     whe
    -0.73
    生死
    -0.71
    galactic
    -0.71
     رمضان
    -0.70
    混沌
    -0.70
    POSITIVE LOGITS
     twentieth
    4.13
     Twentieth
    3.03
     XX
    2.55
    entieth
    2.06
    XX
    1.78
    Tw
    1.64
     century
    1.62
     postwar
    1.51
    tw
    1.42
     mid
    1.41
    Activations Density 0.114%

    No Known Activations