© 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. 43873
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
     Vorteil
    -2.23
    慇
    -2.20
    逡
    -2.17
     الحالي
    -2.16
     zimowa
    -2.14
    indelijk
    -2.14
    OMBIA
    -2.13
    硖
    -2.11
    énieurs
    -2.11
    igrette
    -2.06
    POSITIVE LOGITS
    c
    3.23
    l
    2.84
    d
    2.69
    e
    2.56
    -
    2.50
    寕
    2.48
    F
    2.36
    ia
    2.34
    n
    2.33
    ى
    2.31
    Activations Density 0.001%

    No Known Activations