© 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. 45593
    Prev
    Next
    INDEX
    Explanations

    German word components

    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
    z
    -2.39
    、
    -2.23
     to
    -2.19
    <td>
    -2.14
    c
    -2.09
    f
    -2.08
     by
    -2.08
     for
    -2.06
    B
    -2.03
    —
    -1.99
    POSITIVE LOGITS
    Karakteristik
    2.02
    Fitur
    1.98
     sellado
    1.91
    捽
    1.90
     墊
    1.87
     褲
    1.86
     入り口
    1.77
    jangkau
    1.77
    Şi
    1.77
    咈
    1.73
    Activations Density 0.012%

    No Known Activations