© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74089
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    The neuron detects date expressions, i.e. mentions of months and their adjacent day or year numbers.

    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
    ciclop
    -1.54
    selben
    -1.54
     Belajar
    -1.49
    Any
    -1.45
    是怎么回事
    -1.41
     erzählt
    -1.41
     lámpara
    -1.40
    ❽
    -1.39
     zatím
    -1.38
     you
    -1.34
    POSITIVE LOGITS
     of
    2.50
     but
    1.54
    ただし
    1.46
     innen
    1.34
     with
    1.32
    ()")
    1.31
     behövs
    1.28
     few
    1.24
     händer
    1.21
    ur
    1.18
    Activations Density 0.086%

    No Known Activations