© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39744
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    The neuron activates on multi‐digit numerical tokens, primarily four-digit years and similar date references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    餚
    -1.35
     kalori
    -1.30
    stylish
    -1.25
     dipinto
    -1.22
     schuhe
    -1.20
     kapsul
    -1.19
    饷
    -1.19
     hábit
    -1.19
    饌
    -1.19
     prakti
    -1.18
    POSITIVE LOGITS
     April
    1.53
     July
    1.40
     June
    1.39
    ナメント
    1.38
     August
    1.36
    亟
    1.34
     летом
    1.29
     March
    1.28
     January
    1.20
    づくり
    1.18
    Activations Density 0.049%

    No Known Activations