© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91628
    Prev
    Next
    INDEX
    Explanations

    date:

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

    This neuron detects numeric tokens (especially years, hyphens, and related digits) that form date or timestamp patterns in comments and metadata.

    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
     naar
    -0.82
    了你
    -0.81
     innere
    -0.79
    お待ち
    -0.78
     nossa
    -0.75
    chenden
    -0.71
    Sú
    -0.71
     million
    -0.71
     phenomena
    -0.71
     nossas
    -0.71
    POSITIVE LOGITS
     diferite
    0.81
     eft
    0.80
     Pb
    0.78
     ∆
    0.76
     Reflective
    0.76
     tef
    0.75
     diph
    0.75
     nerv
    0.74
     igno
    0.73
    跹
    0.73
    Activations Density 0.075%

    No Known Activations