© 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. 10-GEMMASCOPE-RES-131K
    7. 72181
    Prev
    Next
    INDEX
    Explanations

    extreme values and outliers

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -2.45
    }$
    -2.17
     vorigen
    -2.13
    a
    -2.05
     櫃
    -1.98
    ‌شده
    -1.94
     selben
    -1.88
    蔼
    -1.86
    一丝
    -1.86
    ahi
    -1.85
    POSITIVE LOGITS
     extraordinaire
    2.61
    erintah
    2.41
     própria
    2.22
    齜
    2.14
    料金
    2.13
     categorically
    2.13
     persistently
    2.11
    ೬
    2.09
     citing
    2.08
    淥
    2.05
    Activations Density 0.001%

    No Known Activations