© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39392
    Prev
    Next
    INDEX
    Explanations

    Mathematical and general descriptive phrases

    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
     Sementara
    -1.51
    🪤
    -1.41
    ceased
    -1.41
    biendo
    -1.39
     getById
    -1.37
    peicher
    -1.36
    Aggi
    -1.36
     Seperti
    -1.35
    ⇴
    -1.35
    leyin
    -1.34
    POSITIVE LOGITS
     touted
    1.58
     presumably
    1.55
     hitherto
    1.54
     various
    1.53
    it
    1.45
     supposedly
    1.42
     presumed
    1.42
     respective
    1.42
     bisher
    1.41
     ordinarily
    1.41
    Activations Density 0.004%

    No Known Activations