© 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. 60395
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
     hopefully
    -1.05
    hopefully
    -1.02
     Hopefully
    -0.87
    しゃぶ
    -0.87
     limpiar
    -0.85
    jenie
    -0.82
    お好み
    -0.82
     etc
    -0.81
    ществ
    -0.80
    FormBuilder
    -0.80
    POSITIVE LOGITS
     two
    1.10
     both
    1.10
    ]';
    1.02
     three
    0.96
    []]
    0.91
     Three
    0.87
     again
    0.86
    ₁(
    0.84
     già
    0.84
    Three
    0.83
    Activations Density 0.024%

    No Known Activations