© 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. 10-GEMMASCOPE-RES-131K
    7. 43066
    Prev
    Next
    INDEX
    Explanations

    day or days

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

    The neuron strongly activates on numeric tokens that represent date or time components (e.g. day, month, year values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ípios
    -1.69
     небольшие
    -1.59
     docentes
    -1.55
    peration
    -1.55
     протяжении
    -1.54
    ཫ
    -1.49
     amounted
    -1.48
     yüzde
    -1.48
    immagine
    -1.47
    เขา
    -1.46
    POSITIVE LOGITS
    翆
    2.08
    ؟
    1.90
     this
    1.80
    髣
    1.79
    It
    1.79
    蛩
    1.79
     необходимо
    1.78
    ༤
    1.73
     های
    1.72
     هایی
    1.71
    Activations Density 0.016%

    No Known Activations