© 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. 39088
    Prev
    Next
    INDEX
    Explanations

    use of your data

    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
    aute
    -0.91
     Reihenfolge
    -0.89
     bedre
    -0.88
    τικές
    -0.87
     cuz
    -0.87
    geta
    -0.87
    ppsala
    -0.86
    líben
    -0.86
     литературы
    -0.86
    Precalculus
    -0.85
    POSITIVE LOGITS
     necessary
    1.32
     your
    1.30
    周泽
    1.24
     may
    1.11
    ־ה
    1.09
     иногда
    1.08
     eventualmente
    0.94
     Gunakan
    0.94
    どういう
    0.93
    可能會
    0.90
    Activations Density 0.021%

    No Known Activations