© 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. 12394
    Prev
    Next
    INDEX
    Explanations

    options after a prompt

    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
     and
    -1.45
    ATIVA
    -1.31
     además
    -1.20
    IRQn
    -1.17
     such
    -1.17
    ACJA
    -1.16
    пами
    -1.16
    abung
    -1.13
    ipfel
    -1.11
     жидко
    -1.10
    POSITIVE LOGITS
     your
    1.55
     you
    1.54
     recortes
    1.38
     یا
    1.32
     yourself
    1.32
     into
    1.29
     или
    1.29
     amables
    1.24
     券
    1.24
     می‌گوید
    1.23
    Activations Density 0.041%

    No Known Activations