© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58695
    Prev
    Next
    INDEX
    Explanations

    reference block

    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
     its
    -0.94
     their
    -0.93
     Ľ
    -0.87
     дефек
    -0.86
    確認ください
    -0.84
    =!
    -0.81
    nations
    -0.80
    劍
    -0.80
     عنه
    -0.80
     klientów
    -0.80
    POSITIVE LOGITS
     drinken
    0.90
     broadening
    0.88
    ƌ
    0.88
    kız
    0.86
     forging
    0.85
    そういった
    0.85
     uwe
    0.82
     wagen
    0.81
    そんな
    0.80
     blotting
    0.80
    Activations Density 0.002%

    No Known Activations