© 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. 22-GEMMASCOPE-RES-131K
    7. 70885
    Prev
    Next
    INDEX
    Explanations

    particles of emphasis

    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
    estaba
    -2.25
    cuando
    -2.14
    Suka
    -2.06
    pregunt
    -2.05
    aceite
    -2.03
    comida
    -2.02
    Makanan
    -1.98
    daß
    -1.96
    Tür
    -1.95
    Öl
    -1.95
    POSITIVE LOGITS
    C
    2.55
    “
    2.50
    t
    2.47
    J
    2.38
    a
    2.33
    '
    2.33
    O
    2.33
     “
    2.27
    y
    2.23
    S
    2.22
    Activations Density 0.009%

    No Known Activations