© 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. 12507
    Prev
    Next
    INDEX
    Explanations

    phrases like "past week", "last year"

    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
     other
    -1.56
     then
    -1.52
    siamo
    -1.51
     herido
    -1.48
    されていました
    -1.47
    през
    -1.45
    がなく
    -1.43
    Controllo
    -1.42
    intelligible
    -1.42
    obatan
    -1.42
    POSITIVE LOGITS
     
    1.75
    w
    1.68
    a
    1.61
    b
    1.49
    "
    1.48
    “
    1.48
    L
    1.48
    c
    1.45
    es
    1.45
    er
    1.44
    Activations Density 0.021%

    No Known Activations