© 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. 106120
    Prev
    Next
    INDEX
    Explanations

    latest and newest

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

    This neuron strongly responds to common function words—especially the definite article “the” and possessive pronouns like “his” and “her.”

    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
    銳
    -0.91
    ModelAdmin
    -0.89
    明年
    -0.88
     propia
    -0.87
    込んだ
    -0.85
     Existing
    -0.84
    marginHorizontal
    -0.83
    unton
    -0.83
    ưu
    -0.81
     maiores
    -0.81
    POSITIVE LOGITS
     latest
    8.13
    latest
    6.19
    Latest
    5.47
     newest
    4.94
     Latest
    4.69
    最新
    4.66
    最新的
    4.44
     LATEST
    4.13
    LATEST
    4.00
    ล่า
    3.73
    Activations Density 0.211%

    No Known Activations