© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65529
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    zionare
    -1.17
     joyería
    -1.17
    Quién
    -1.14
     коше
    -1.14
     its
    -1.14
     sindic
    -1.13
     redaktion
    -1.12
     Meksi
    -1.11
     Spanyol
    -1.11
     背影
    -1.10
    POSITIVE LOGITS
     and
    1.47
    ’
    1.07
    !
    1.05
    ↵↵↵↵
    1.03
    '
    1.02
    .
    0.97
    ↵↵↵
    0.94
    AC
    0.93
    AB
    0.91
     принтом
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.