© 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. 68123
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     certainement
    -1.04
    scars
    -0.94
    jours
    -0.94
     tamaños
    -0.94
     execução
    -0.93
    мови
    -0.92
    everybody
    -0.92
     dôle
    -0.91
    に行った
    -0.91
    çok
    -0.91
    POSITIVE LOGITS
     two
    1.02
    ią
    0.96
    因为他
    0.93
    ®,
    0.93
     these
    0.92
    缴
    0.90
     Usually
    0.89
    ®
    0.88
    ativamente
    0.88
     app
    0.87
    Activations Density 0.000%

    No Known Activations