© 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. 103164
    Prev
    Next
    INDEX
    Explanations

    data applications

    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
     thinking
    -0.85
     naudoti
    -0.81
     vegetation
    -0.74
    atalyst
    -0.73
     kaki
    -0.73
    Ingredientes
    -0.69
     ARB
    -0.69
    Digital
    -0.68
     utilizzando
    -0.68
     ニュース
    -0.68
    POSITIVE LOGITS
     rate
    1.12
    RATE
    1.04
    rate
    1.02
     RATE
    1.00
     Rate
    0.92
    流し
    0.88
     komunikasi
    0.85
    Rate
    0.84
    の流れ
    0.83
     tanggung
    0.82
    Activations Density 0.077%

    No Known Activations