© 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. 71644
    Prev
    Next
    INDEX
    Explanations

    English sentence starters

    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
     الجلد
    -0.93
     of
    -0.90
    *<
    -0.83
    herstellung
    -0.82
    ⬇️
    -0.82
     lưới
    -0.81
     euró
    -0.80
    ordi
    -0.79
    мили
    -0.79
    ORDIN
    -0.78
    POSITIVE LOGITS
    oved
    1.04
    unno
    1.02
     explaining
    0.95
     weichen
    0.94
    ουν
    0.93
     aborto
    0.92
    stě
    0.92
    elis
    0.90
    Quiénes
    0.90
     Italij
    0.90
    Activations Density 0.118%

    No Known Activations