© 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. 10-GEMMASCOPE-RES-131K
    7. 10990
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or lists

    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_10/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
     temporaire
    -1.48
     sichere
    -1.34
    дзі
    -1.32
    \.
    -1.29
    ки
    -1.28
     bulu
    -1.27
    を
    -1.27
    чика
    -1.27
     gorro
    -1.27
     recomendado
    -1.26
    POSITIVE LOGITS
     will
    1.67
    .”
    1.46
     including
    1.39
    ઃ
    1.38
     alongside
    1.32
     includes
    1.31
    んびり
    1.30
    ではでは
    1.29
    同上
    1.28
     include
    1.27
    Activations Density 0.109%

    No Known Activations