© 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. 34-GEMMASCOPE-RES-131K
    7. 33052
    Prev
    Next
    INDEX
    Explanations

    garage rock, surf music

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

    The neuron strongly activates on numeric tokens that represent years or decades (e.g. “1960s,” “1981,” “1957”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    íncipe
    -0.71
     مان
    -0.70
     foldable
    -0.67
     workforce
    -0.67
     philosophies
    -0.66
     Ithaca
    -0.66
     hypoxia
    -0.65
     эко
    -0.65
     приро
    -0.65
    يه
    -0.64
    POSITIVE LOGITS
     surf
    1.48
     surfing
    1.25
     reverb
    1.24
     garage
    1.23
     Surf
    1.22
    surf
    1.20
    garage
    1.15
     Surfing
    1.09
    Surf
    1.08
    Garage
    1.00
    Activations Density 0.030%

    No Known Activations