© 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. 99552
    Prev
    Next
    INDEX
    Explanations

    sayings and proverbs

    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
     to
    -2.27
     your
    -1.59
     like
    -1.45
     flexível
    -1.35
     of
    -1.35
     filós
    -1.30
    蛲
    -1.29
     satria
    -1.26
     móvel
    -1.26
     verarbeitet
    -1.23
    POSITIVE LOGITS
    ícias
    1.35
    tifiable
    1.34
    cją
    1.26
    >|</
    1.25
    tablissements
    1.25
    eradish
    1.22
    isome
    1.21
    isait
    1.20
    itudinal
    1.19
    omato
    1.18
    Activations Density 0.223%

    No Known Activations