© 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. 22-GEMMASCOPE-RES-131K
    7. 34727
    Prev
    Next
    INDEX
    Explanations

    abbreviations and specific words

    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
    。
    -0.99
     прекрасно
    -0.90
     permitió
    -0.87
    ።
    -0.85
     hängt
    -0.83
     braucht
    -0.82
    Öl
    -0.81
     réessayer
    -0.79
    querque
    -0.79
    Mí
    -0.79
    POSITIVE LOGITS
    はその
    1.05
     means
    0.97
     fyra
    0.96
     lisa
    0.95
    琛
    0.95
     täv
    0.91
     ')'
    0.90
     diego
    0.90
     deras
    0.89
     vicente
    0.89
    Activations Density 0.069%

    No Known Activations