© 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. 66856
    Prev
    Next
    INDEX
    Explanations

    typos for the

    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
    ፨
    -2.41
     tijdens
    -2.20
    
    -2.19
    
    -2.17
     consulte
    -2.17
    ⃢
    -2.16
    鹀
    -2.16
     meestal
    -2.16
    vereignty
    -2.13
     THEM
    -2.09
    POSITIVE LOGITS
     These
    2.52
    There
    2.48
     This
    2.42
    {
    2.36
     very
    2.31
     terdekat
    2.30
     Since
    2.28
     two
    2.28
     этим
    2.23
     first
    2.22
    Activations Density 0.031%

    No Known Activations