© 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. 109356
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    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
    নের
    -1.01
     золота
    -0.87
    引言
    -0.86
    靭
    -0.86
    Generally
    -0.85
    ！(
    -0.85
    辞典
    -0.82
     tunt
    -0.82
     barna
    -0.82
     Generally
    -0.81
    POSITIVE LOGITS
     havet
    1.04
     появится
    1.01
    っており
    1.00
    gives
    0.98
    ◦
    0.96
     む
    0.95
    Õ
    0.95
    athed
    0.95
    —-
    0.94
     ($("#
    0.94
    Activations Density 0.003%

    No Known Activations