© 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. 24907
    Prev
    Next
    INDEX
    Explanations

    early periods

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

    The neuron selectively responds to numeric tokens that are part of four‐digit years or decade notations (e.g. “1970s,” “1950s,” “1990s”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     and
    -1.57
     or
    -1.30
    CCIÓN
    -1.00
     depuis
    -0.98
     misschien
    -0.97
    Ayrıca
    -0.97
    kegiatan
    -0.96
    trab
    -0.95
     silty
    -0.95
     day
    -0.93
    POSITIVE LOGITS
     électron
    1.15
    thmus
    1.02
    蘂
    1.02
     hunde
    1.02
     gâteau
    1.01
    yourself
    0.98
     tabela
    0.98
    vaila
    0.97
     notor
    0.97
    疝
    0.96
    Activations Density 0.031%

    No Known Activations