© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    born in year

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

    The neuron is detecting four‐digit year numbers (e.g. birth years and other date markers).

    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
     and
    -1.22
    F
    -1.11
    T
    -1.02
    .*")]
    -0.98
    P
    -0.98
    B
    -0.97
    PREFERRED
    -0.95
    ul
    -0.94
    Stroke
    -0.93
    -0.92
    POSITIVE LOGITS
     fré
    1.27
     kontinu
    1.24
    Tentang
    1.14
     autorisation
    1.14
    iç
    1.12
    yaitu
    1.10
    Produktion
    1.09
     occhiali
    1.07
    Komple
    1.07
    Karakter
    1.07
    Activations Density 0.034%

    No Known Activations