© 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. 105914
    Prev
    Next
    INDEX
    Explanations

    naval and watercraft terms

    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
     your
    -1.74
    טים
    -1.72
    葑
    -1.51
    槤
    -1.46
    Oktober
    -1.44
    あなたの
    -1.41
     autentic
    -1.39
    viste
    -1.39
     primas
    -1.39
     diametro
    -1.37
    POSITIVE LOGITS
     L
    1.59
    </i>
    1.52
     üb
    1.45
     This
    1.41
     l
    1.40
     Dritte
    1.39
     A
    1.39
    to
    1.38
     With
    1.38
     o
    1.37
    Activations Density 0.238%

    No Known Activations