© 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. 35726
    Prev
    Next
    INDEX
    Explanations

    time references, past and present

    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
     parlare
    -1.09
     inspiradoras
    -1.00
     since
    -1.00
     seguras
    -0.96
     ہے۔
    -0.96
    Dres
    -0.94
    kenalkan
    -0.94
     almacenamiento
    -0.94
     iniciales
    -0.93
     altavoz
    -0.93
    POSITIVE LOGITS
     Now
    1.45
     now
    1.38
     ahora
    1.35
    Now
    1.28
     will
    1.15
    now
    1.11
     was
    1.07
     Ahora
    0.96
     agora
    0.96
     cuando
    0.96
    Activations Density 0.059%

    No Known Activations