© 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. 93920
    Prev
    Next
    INDEX
    Explanations

    good luck wishes

    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
     a
    -1.03
     by
    -0.95
     so
    -0.95
    celotti
    -0.95
    必要があります
    -0.94
     nachdem
    -0.93
    最有
    -0.93
     kurzer
    -0.93
     faites
    -0.91
     vital
    -0.90
    POSITIVE LOGITS
     and
    1.31
     wishes
    1.30
     whichever
    1.24
    และ
    1.13
    你的
    1.11
     in
    1.09
     on
    1.05
    hichever
    1.03
    gingen
    1.03
    素敵な
    1.02
    Activations Density 0.005%

    No Known Activations