© 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. 22-GEMMASCOPE-RES-131K
    4. 70606
    Prev
    Next
    INDEX
    Explanations

    temporary modifications and states

    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
     wichtigste
    -2.45
    OUTUBE
    -2.44
     perfekte
    -2.34
    沵
    -2.31
     famed
    -2.28
     reconhe
    -2.23
     dritte
    -2.23
     astonishing
    -2.23
    ܞ
    -2.22
     fazendo
    -2.20
    POSITIVE LOGITS
    just
    2.64
    what
    2.52
    you
    2.41
    ”,
    2.31
     noteworthy
    2.27
     cleverly
    2.25
     heightened
    2.25
     decreases
    2.22
     Through
    2.22
     getting
    2.22
    Activations Density 0.011%

    No Known Activations