© 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. 22-GEMMASCOPE-RES-131K
    4. 70919
    Prev
    Next
    INDEX
    Explanations

    works fine, but

    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_22/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
     this
    -1.02
     efekt
    -0.98
     juguete
    -0.98
     perjuangan
    -0.91
    laması
    -0.91
     stalo
    -0.91
     menghilangkan
    -0.87
    responsibility
    -0.86
     preciosa
    -0.85
    icznej
    -0.84
    POSITIVE LOGITS
     even
    1.20
     sogar
    1.14
    even
    1.10
     навіть
    1.06
     даже
    1.06
     anzi
    1.02
     bahkan
    0.98
     incluso
    0.97
     thậm
    0.96
    GEBURTS
    0.94
    Activations Density 0.120%

    No Known Activations