© 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. 10-GEMMASCOPE-RES-131K
    7. 20370
    Prev
    Next
    INDEX
    Explanations

    1970s, 1980s, 1990s

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

    The neuron detects decade references (e.g. “80s,” “90s,” etc.).

    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
     and
    -2.09
    ’
    -1.92
    The
    -1.86
     here
    -1.77
     there
    -1.76
     sio
    -1.66
    '
    -1.60
     Anſ
    -1.58
     verschied
    -1.58
     is
    -1.58
    POSITIVE LOGITS
     sehr
    2.16
    ቭ
    2.06
     heridas
    1.98
     ruthless
    1.95
     makeshift
    1.93
     virtudes
    1.90
     evade
    1.80
     \
    1.80
     municipales
    1.80
     \{
    1.78
    Activations Density 0.058%

    No Known Activations