© 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. 3479
    Prev
    Next
    INDEX
    Explanations

    listing ages

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    wość
    -0.94
    每
    -0.89
    일본
    -0.85
    𝗦
    -0.83
     nettsted
    -0.82
     besz
    -0.82
     اللاعب
    -0.82
     so
    -0.80
    𝗔
    -0.78
    ֿ
    -0.78
    POSITIVE LOGITS
     age
    1.02
    ぽん
    1.00
    あっという
    0.98
    すっ
    0.98
    Fuß
    0.95
    背面
    0.93
    えっ
    0.93
     רק
    0.91
    活用
    0.90
    哎呀
    0.90
    Activations Density 0.021%

    No Known Activations