© 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. 25052
    Prev
    Next
    INDEX
    Explanations

    material qualities

    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
    tamol
    -1.34
    redientes
    -1.16
     ChromeDriver
    -1.06
     sockaddr
    -1.04
     to
    -1.02
    ophobic
    -1.01
    abinieri
    -1.01
    breos
    -1.00
    carus
    -0.99
    了什么
    -0.99
    POSITIVE LOGITS
     restauración
    1.06
     reparación
    1.06
    fø
    1.03
     soigneusement
    1.01
     warszawa
    0.98
     añadido
    0.98
     Reinigung
    0.97
    worpen
    0.96
    yet
    0.96
     qualities
    0.95
    Activations Density 0.054%

    No Known Activations