© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68216
    Prev
    Next
    INDEX
    Explanations

    domain names ending in .com

    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
     while
    -1.54
     .
    -1.48
     any
    -1.46
     either
    -1.38
     only
    -1.36
    ).
    -1.33
    なー
    -1.27
     FOR
    -1.23
    他又
    -1.22
     for
    -1.20
    POSITIVE LOGITS
    uestion
    1.53
    穽
    1.48
    ться
    1.45
     wła
    1.41
     Lalu
    1.39
     ULTRA
    1.38
     シルエット
    1.37
    תיים
    1.34
    CHOOL
    1.34
    usiness
    1.33
    Activations Density 0.023%

    No Known Activations