© 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. 34-GEMMASCOPE-RES-131K
    7. 47046
    Prev
    Next
    INDEX
    Explanations

    initials or abbreviations

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﱠ
    -1.18
     Раз
    -0.91
     упаковка
    -0.91
     what
    -0.89
     Décembre
    -0.88
     TWO
    -0.87
     Александра
    -0.87
    tifacts
    -0.85
     otro
    -0.84
    RoleId
    -0.84
    POSITIVE LOGITS
     solle
    1.05
    cti
    1.00
    ț
    0.98
    zcze
    0.96
    endung
    0.95
     adatt
    0.94
     sx
    0.93
    Odkazy
    0.91
    öra
    0.90
     mse
    0.90
    Activations Density 0.486%

    No Known Activations