© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75720
    Prev
    Next
    INDEX
    Explanations

    prepaid payment cost negative nonnegative

    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
     elektrische
    -2.38
     beinahe
    -2.36
     reichlich
    -2.28
    {
    -2.11
     kleinere
    -2.11
     zweifel
    -2.09
     ポーズ
    -2.08
     kräf
    -2.06
     vorne
    -2.06
     schwach
    -2.05
    POSITIVE LOGITS
     According
    2.27
     in
    2.13
     During
    2.06
    Ⲉ
    2.06
     What
    1.98
     Using
    1.97
     However
    1.96
     Especially
    1.94
     Compared
    1.90
    ligators
    1.87
    Activations Density 0.004%

    No Known Activations