© 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. 45470
    Prev
    Next
    INDEX
    Explanations

    Japanese katakana words

    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
    in
    -2.86
    that
    -2.69
    it
    -2.56
     стоковая
    -2.47
    其他
    -2.30
     dikutip
    -2.23
    景色
    -2.16
     are
    -2.13
    en
    -2.06
     And
    -2.05
    POSITIVE LOGITS
    轫
    2.72
    tedì
    2.70
     '',
    2.70
    ſſen
    2.69
    
    2.44
    还挺
    2.41
    秝
    2.41
    ophageal
    2.36
    cellor
    2.34
    arwal
    2.34
    Activations Density 0.002%

    No Known Activations