© 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. 32749
    Prev
    Next
    INDEX
    Explanations

    replace with the word

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

    The neuron activates on numeral tokens (numeric values) in the text.

    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
     téměř
    -0.95
     několika
    -0.94
    FirstResponder
    -0.93
     мимо
    -0.93
    thschild
    -0.92
     folgender
    -0.91
    っけ
    -0.90
    瀧
    -0.90
    etration
    -0.89
    ジナル
    -0.89
    POSITIVE LOGITS
     replace
    1.73
     replacing
    1.70
     replaces
    1.66
    replace
    1.66
     Replace
    1.59
     replaced
    1.49
    Replace
    1.45
     REPLACE
    1.39
     Substitute
    1.37
     Replacement
    1.34
    Activations Density 0.046%

    No Known Activations