© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128113
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the phrase “over the years,” i.e. references to a long‐term time span.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    over the years

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     one
    -2.05
     after
    -1.96
     when
    -1.87
     before
    -1.85
     first
    -1.78
     two
    -1.66
     at
    -1.60
     without
    -1.59
     begins
    -1.52
     immediately
    -1.51
    POSITIVE LOGITS
     diverses
    2.00
     verschillende
    1.91
     różnych
    1.82
     várias
    1.80
    various
    1.79
    several
    1.67
     diversos
    1.63
     différentes
    1.62
     différents
    1.57
     DIFFERENT
    1.57
    Activations Density 0.041%

    No Known Activations