© 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. 68270
    Prev
    Next
    INDEX
    Explanations

    website navigation separators

    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
     they
    -1.01
    沢山
    -0.99
     fresca
    -0.99
    พวก
    -0.96
     They
    -0.95
     ihres
    -0.94
     fonde
    -0.94
    collant
    -0.91
     barrera
    -0.91
    他们
    -0.89
    POSITIVE LOGITS
     to
    1.03
     específicamente
    1.02
    ñora
    0.94
     mondeo
    0.87
    ítása
    0.87
     intitulée
    0.87
     такого
    0.86
     אוי
    0.86
    ]$.
    0.86
    Према
    0.86
    Activations Density 0.037%

    No Known Activations