© 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. 22-GEMMASCOPE-RES-131K
    7. 14676
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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_22/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
     ایالات
    -0.99
    Trend
    -0.91
    らかに
    -0.90
    coda
    -0.88
     bandoulière
    -0.82
     ($("#
    -0.80
    .
    -0.79
    ごはん
    -0.79
     then
    -0.78
     /\.
    -0.77
    POSITIVE LOGITS
    Verweise
    1.02
    ဢ
    0.94
     amounted
    0.93
    solicited
    0.91
    tande
    0.91
    ̀nh
    0.90
     disfrutar
    0.90
    𝟑
    0.89
     their
    0.88
     remedied
    0.86
    Activations Density 0.010%

    No Known Activations