© 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. 34-GEMMASCOPE-RES-131K
    7. 98277
    Prev
    Next
    INDEX
    Explanations

    assignment and expression operators

    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
    所示
    -0.88
    eqn
    -0.86
    deliver
    -0.85
    喊道
    -0.85
     romantis
    -0.84
     erforder
    -0.82
     fortu
    -0.80
    オススメ
    -0.79
     reng
    -0.77
     Europese
    -0.77
    POSITIVE LOGITS
     medalla
    1.08
     varför
    0.93
     chop
    0.89
     każdej
    0.88
     głównie
    0.84
    就行了
    0.84
    齟
    0.84
     bolsas
    0.84
     occupational
    0.83
     holdt
    0.83
    Activations Density 0.050%

    No Known Activations