© 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. 100798
    Prev
    Next
    INDEX
    Explanations

    common practice to

    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
    ре
    -1.48
    蓠
    -1.46
    {
    -1.39
    ле
    -1.35
     effec
    -1.30
    для
    -1.27
    ル
    -1.27
    ро
    -1.27
    ве
    -1.26
     hecha
    -1.26
    POSITIVE LOGITS
    することも
    1.40
     choisissez
    1.35
     after
    1.35
     those
    1.34
    してほしい
    1.31
     découvrez
    1.30
     prenez
    1.29
     pensez
    1.28
    ồm
    1.27
    bahasa
    1.27
    Activations Density 0.084%

    No Known Activations