© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66495
    Prev
    Next
    INDEX
    Explanations

    natural

    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_10/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
    ))
    -1.66
    కర్య
    -1.45
    >';
    -1.45
    ném
    -1.40
     einem
    -1.36
    젊
    -1.33
     zanim
    -1.31
     ";
    -1.27
     Metals
    -1.27
    )):
    -1.27
    POSITIVE LOGITS
    natural
    2.11
     natürliche
    2.02
     naturale
    1.95
     of
    1.95
     natural
    1.92
     自然
    1.85
     naturally
    1.78
     NATURAL
    1.71
     naturales
    1.69
    自然
    1.67
    Activations Density 0.078%

    No Known Activations