© 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. 130250
    Prev
    Next
    INDEX
    Explanations

    favorite new creations

    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
     Configuración
    -1.24
    需要注意
    -1.20
    комплект
    -1.13
    还需要
    -1.07
     herhangi
    -1.02
     Consultado
    -1.02
     вовсе
    -1.02
     zwing
    -1.02
     persoonlijke
    -1.01
     exitoso
    -0.99
    POSITIVE LOGITS
     these
    2.11
     this
    1.64
    these
    1.39
     them
    1.30
     elegan
    1.16
     something
    1.13
    newArray
    1.13
     творо
    1.13
     символ
    1.13
    `;
    1.13
    Activations Density 0.039%

    No Known Activations