© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130391
    Prev
    Next
    INDEX
    Explanations

    common continuations of words

    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
    ),
    -1.14
    levis
    -1.08
     should
    -1.08
     them
    -1.07
     it
    -1.05
     who
    -1.05
    mitsub
    -1.05
    gigi
    -1.02
     only
    -1.02
     last
    -1.02
    POSITIVE LOGITS
    kiet
    1.06
    ◾
    1.05
    Ingredi
    1.04
    macOS
    1.03
     прокура
    1.01
     防止
    1.00
    Zutaten
    1.00
    eigh
    0.99
    眉头
    0.98
    GIF
    0.97
    Activations Density 0.000%

    No Known Activations