© 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. 336
    Prev
    Next
    INDEX
    Explanations

    birth and death years

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

    The neuron is activated by numeric tokens that form birth–death years (date spans in parentheses).

    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
     cincin
    -1.27
     staffel
    -1.24
     lupo
    -1.20
     THEATRE
    -1.16
    を開始
    -1.16
    멧
    -1.16
     hwnd
    -1.16
     OREGON
    -1.15
    ()\
    -1.14
     gti
    -1.13
    POSITIVE LOGITS
     Wünsche
    1.07
     to
    1.07
     geschaffen
    1.05
    2
    0.98
     Eventually
    0.96
     życia
    0.94
     uiteindelijk
    0.92
     obce
    0.91
    ٴ
    0.91
    Ответить
    0.88
    Activations Density 0.060%

    No Known Activations