© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14801
    Prev
    Next
    INDEX
    Explanations

    i didn't followed by verb

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

    The neuron strongly activates on the “’t” ending of English negative contractions (e.g. didn’t, isn’t).

    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
     now
    -1.96
     书法
    -1.86
     currently
    -1.78
    铩
    -1.77
     jums
    -1.75
     inquisitive
    -1.74
    锒
    -1.73
    最后由
    -1.72
     novelas
    -1.70
     fundamentos
    -1.70
    POSITIVE LOGITS
    '
    2.59
    i
    2.19
    [
    2.17
     originally
    1.83
     volna
    1.81
            
    1.80
     бы
    1.79
    도
    1.69
    衕
    1.68
    ’
    1.67
    Activations Density 0.023%

    No Known Activations