© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100151
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
     Mitteln
    -2.61
     desbloquear
    -2.56
     to
    -2.56
     facilitar
    -2.47
     nejlepší
    -2.34
    
    -2.30
     fortalecer
    -2.27
     ayudan
    -2.25
     optimizar
    -2.22
     activar
    -2.19
    POSITIVE LOGITS
    ↵
    5.94
    5
    3.00
    9
    2.95
    4
    2.45
    n
    2.42
     große
    2.42
    d
    2.41
     tetapi
    2.38
    ︐
    2.34
    渼
    2.30
    Activations Density 0.214%

    No Known Activations