© 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. 129908
    Prev
    Next
    INDEX
    Explanations

    didn't know existed

    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
     originalen
    -1.27
    isieren
    -1.16
     некоторых
    -1.09
    ―――
    -1.05
     jeweiligen
    -1.04
    さて
    -1.03
    gewöhn
    -1.02
     Она
    -0.98
     späteren
    -0.96
    ではなく
    -0.96
    POSITIVE LOGITS
     there
    1.87
     aż
    1.72
     this
    1.59
     until
    1.55
    !
    1.50
     such
    1.49
     jusqu
    1.27
     so
    1.27
     even
    1.24
    こんなに
    1.23
    Activations Density 0.017%

    No Known Activations