© 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. 54309
    Prev
    Next
    INDEX
    Explanations

    start of specific phrases

    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
     cleverly
    -0.94
    <u>
    -0.92
     ironically
    -0.90
     hoping
    -0.84
     their
    -0.84
     wybrać
    -0.81
     all
    -0.81
     everything
    -0.80
    暂无
    -0.79
    昀
    -0.78
    POSITIVE LOGITS
    תּ
    1.05
    嵙
    0.98
    Etape
    0.97
    Ȉ
    0.95
    upto
    0.94
    ")]
    0.94
     compiles
    0.94
     gemacht
    0.93
    ilion
    0.93
    talt
    0.93
    Activations Density 0.000%

    No Known Activations