© 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. 15508
    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
     встречи
    -1.11
     Obtén
    -1.03
    ferred
    -1.02
    ጺ
    -1.02
    students
    -1.02
    EdgeInsets
    -1.00
     трубы
    -1.00
     onResume
    -0.99
     sagt
    -0.97
     gramos
    -0.96
    POSITIVE LOGITS
     nuevamente
    1.13
     двигатель
    1.11
    ("")]
    1.11
    Мы
    1.10
    一起
    1.07
    aiuto
    1.05
     ぼ
    1.02
    edakan
    1.01
     frecuentemente
    0.95
     завжди
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.