© 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. 34-GEMMASCOPE-RES-131K
    4. 110675
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

    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_34/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
     THERE
    -1.17
    なのでしょう
    -1.17
    をかける
    -1.16
    なのかな
    -1.15
    ものである
    -1.15
    必要があります
    -1.15
     нынеш
    -1.13
    Cual
    -1.11
    ようになった
    -1.11
    をする
    -1.11
    POSITIVE LOGITS
     with
    2.16
    且
    1.48
     and
    1.44
     throughout
    1.38
     would
    1.27
     without
    1.26
     but
    1.23
     despite
    1.10
     affair
    1.09
    しかも
    1.09
    Activations Density 0.061%

    No Known Activations