© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16420
    Prev
    Next
    INDEX
    Explanations

    historical events and states

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

    The neuron strongly responds to numeric and date‐like tokens (years, century markers, numbered items) in the text.

    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
    ಪ
    -0.86
    Recycle
    -0.86
     douleur
    -0.85
     Zlat
    -0.82
     WRAP
    -0.82
    ofila
    -0.82
     végétal
    -0.81
    ＇
    -0.81
     capt
    -0.81
    ⁸
    -0.81
    POSITIVE LOGITS
     March
    0.95
     calm
    0.92
     emergency
    0.89
     profundas
    0.88
     Now
    0.88
     slow
    0.86
     crisis
    0.84
    pagnol
    0.82
     resilience
    0.81
     May
    0.79
    Activations Density 0.067%

    No Known Activations