© 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. 27293
    Prev
    Next
    INDEX
    Explanations

    cold storage

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ทั้ง
    -1.02
    がありますが
    -1.02
     necesita
    -1.01
    もありますが
    -1.00
     várias
    -0.97
     need
    -0.95
     effets
    -0.94
     plusieurs
    -0.93
    隂
    -0.92
    眼里
    -0.91
    POSITIVE LOGITS
    Those
    1.22
     that
    1.19
     །
    1.18
    There
    1.12
     aquella
    1.04
    значение
    1.04
    könyv
    1.03
    Kā
    1.02
    While
    1.00
    сумка
    1.00
    Activations Density 0.003%

    No Known Activations