© 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. 34-GEMMASCOPE-RES-131K
    7. 62409
    Prev
    Next
    INDEX
    Explanations

    page numbers and references

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

    The neuron is strongly activated by tokens consisting of three-digit numbers.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    続きを読む
    -1.04
    También
    -0.99
    を選択します
    -0.95
     Maßnahmen
    -0.95
    」、
    -0.94
    这事
    -0.92
    März
    -0.91
    vejec
    -0.91
    ("\
    -0.91
    Además
    -0.90
    POSITIVE LOGITS
     pp
    1.36
    borns
    1.05
    ⌥
    1.02
    ,
    0.98
    hounds
    0.98
     misalnya
    0.94
    っており
    0.93
    臓
    0.92
    erals
    0.92
    ｯ
    0.92
    Activations Density 0.006%

    No Known Activations