© 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. 10-GEMMASCOPE-RES-131K
    7. 102592
    Prev
    Next
    INDEX
    Explanations

    locations and boundaries

    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
     then
    -1.52
     компьютера
    -1.46
    苼
    -1.45
    を使う
    -1.42
    Ď
    -1.40
     殼
    -1.34
     nemlig
    -1.34
     vanille
    -1.33
     イラストレーション
    -1.33
    了下
    -1.29
    POSITIVE LOGITS
     Hinsicht
    1.45
     where
    1.40
    erintah
    1.39
    既に
    1.33
     nyel
    1.30
     some
    1.28
    nitř
    1.27
    erevan
    1.26
     antiguas
    1.24
     pastel
    1.23
    Activations Density 0.081%

    No Known Activations