© 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. 25416
    Prev
    Next
    INDEX
    Explanations

    after or chronological sequence

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

    The neuron responds to numeric tokens—years, scores, statistics, and other numbers—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
    abytes
    -0.80
    enser
    -0.75
    就连
    -0.74
     vitara
    -0.74
    ja
    -0.73
    +(
    -0.72
    time
    -0.72
    XL
    -0.72
    hies
    -0.72
    age
    -0.71
    POSITIVE LOGITS
     afterwards
    1.20
     danach
    1.11
     selepas
    1.09
     after
    1.05
     afterward
    1.03
     після
    1.01
    之后
    0.98
    之前
    0.96
    Afterwards
    0.96
    katapos
    0.95
    Activations Density 0.048%

    No Known Activations