© 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. 22-GEMMASCOPE-RES-131K
    7. 93306
    Prev
    Next
    INDEX
    Explanations

    date and following punctuation

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

    The neuron detects occurrences of the token “date” used in document metadata or markup (e.g. front-matter or commands).

    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
    ごとの
    -1.26
     their
    -1.23
     it
    -1.23
    に入れる
    -1.20
    AxisSize
    -1.20
    mazda
    -1.19
     twij
    -1.15
     francia
    -1.15
    際に
    -1.13
    だと思う
    -1.13
    POSITIVE LOGITS
    &
    1.02
    tablename
    1.00
    <>
    0.99
     учителя
    0.98
     NIE
    0.98
    やろ
    0.97
    excellents
    0.95
    融合
    0.94
    המ
    0.94
    テイ
    0.91
    Activations Density 0.001%

    No Known Activations