© 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. 10-GEMMASCOPE-RES-131K
    7. 61370
    Prev
    Next
    INDEX
    Explanations

    picked up

    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_10/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
    *
    -1.73
    ↵↵
    -1.69
    Â
    -1.65
     交換
    -1.62
    Ã
    -1.58
    (!)
    -1.52
     a
    -1.49
     "
    -1.41
    er
    -1.41
    [
    -1.40
    POSITIVE LOGITS
    например
    1.59
     donnent
    1.52
    Ւ
    1.51
     informar
    1.47
     Atención
    1.43
     אין
    1.42
     bijvoorbeeld
    1.42
    なども
    1.35
    kazuje
    1.35
    ләр
    1.35
    Activations Density 0.034%

    No Known Activations