© 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. 64452
    Prev
    Next
    INDEX
    Explanations

    usually, often, frequently

    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
    laş
    -0.82
    関連項目
    -0.81
    [@"
    -0.81
    ёх
    -0.80
    ㅇ
    -0.80
    lop
    -0.77
     Linie
    -0.77
     همچنین
    -0.77
    愤怒
    -0.77
     hí
    -0.76
    POSITIVE LOGITS
     usually
    1.50
    Usually
    1.24
     обычно
    1.12
     généralement
    1.11
    usually
    1.07
     Usually
    1.06
     Chúng
    1.02
     often
    1.01
     vždy
    1.00
    解決
    0.98
    Activations Density 0.127%

    No Known Activations