© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27308
    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
     دخترانه
    -0.89
    哪怕
    -0.88
     تغذیه
    -0.88
    фора
    -0.86
    FAM
    -0.86
     tendency
    -0.84
    —”
    -0.84
     sker
    -0.83
     الشاشة
    -0.83
    それを
    -0.83
    POSITIVE LOGITS
     your
    1.12
     وزار
    1.05
    Tep
    1.02
     الحكومة
    1.02
     pessoa
    1.00
    Workout
    0.90
    cketed
    0.90
     trám
    0.89
     läm
    0.86
     Yên
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.