© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34532
    Prev
    Next
    INDEX
    Explanations

    old, outdated, or archaic

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

    This neuron activates on mentions of time references or historical eras (e.g. “something from the ’80s,” “artifact from 2008,” “Jim Crow era”).

    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
     resourceCulture
    -1.01
    骼
    -0.87
    рецепт
    -0.85
     bislang
    -0.85
     restruct
    -0.82
     vorher
    -0.80
     schwierig
    -0.78
    🕧
    -0.75
    ificato
    -0.75
     derzeit
    -0.75
    POSITIVE LOGITS
     outdated
    1.78
     dated
    1.68
     still
    1.38
    dated
    1.34
     old
    1.30
    Dated
    1.25
     DATED
    1.24
     archaic
    1.20
     anachron
    1.17
     obsolete
    1.15
    Activations Density 0.068%

    No Known Activations