© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84390
    Prev
    Next
    INDEX
    Explanations

    for loop index

    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
     requieren
    -1.15
    になるので
    -1.06
     причине
    -1.05
     proporcionan
    -1.04
     rebajas
    -1.03
     navegar
    -1.02
     acoso
    -1.02
     personalizar
    -1.02
     admiten
    -1.00
     aplican
    -1.00
    POSITIVE LOGITS
     pasaran
    1.14
    ペーパー
    1.06
     verdure
    1.05
     what
    1.01
     dici
    1.00
     Layers
    0.99
     tasse
    0.98
    ⚪
    0.98
     biografi
    0.98
     jScrollPane
    0.97
    Activations Density 0.006%

    No Known Activations