© 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. 33597
    Prev
    Next
    INDEX
    Explanations

    years and months

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

    The neuron fires on numeric tokens—especially multi‐digit numbers representing years, dates, ages, counts, or similar quantitative values.

    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
     opposing
    -0.88
    HIGHLIGHTS
    -0.83
    rollup
    -0.82
    嘛
    -0.81
    PUBL
    -0.78
     overall
    -0.76
    αν
    -0.76
    ابل
    -0.76
     might
    -0.75
    adita
    -0.75
    POSITIVE LOGITS
     Mere
    0.89
    sole
    0.88
    знать
    0.88
     jusque
    0.85
    ttle
    0.84
    recent
    0.84
    ffre
    0.81
    佩服
    0.80
    ⲥ
    0.80
     исключительно
    0.79
    Activations Density 0.066%

    No Known Activations