© 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. 22-GEMMASCOPE-RES-131K
    7. 64268
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    —
    -1.29
    還能
    -1.16
    vid
    -1.15
    ler
    -1.15
    ara
    -1.13
    se
    -1.12
    ith
    -1.12
     システム
    -1.11
    mit
    -1.11
    ig
    -1.11
    POSITIVE LOGITS
    ୈ
    1.38
     خواهد
    1.34
    sistencia
    1.27
    държа
    1.20
    﨑
    1.19
    珦
    1.17
    某些
    1.15
     Debussy
    1.14
    резать
    1.14
    سطس
    1.14
    Activations Density 0.014%

    No Known Activations