© 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. 34-GEMMASCOPE-RES-131K
    7. 53942
    Prev
    Next
    INDEX
    Explanations

    time stamps 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_34/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
    რ
    -0.79
     wani
    -0.77
    RelativeTo
    -0.77
    ится
    -0.77
    Dig
    -0.77
    shared
    -0.77
    τα
    -0.75
     تن
    -0.75
    Until
    -0.74
    Tonight
    -0.73
    POSITIVE LOGITS
     madrugada
    1.00
     early
    0.85
    Destroyer
    0.84
    EARLY
    0.80
     Dhaka
    0.79
     togg
    0.79
     GSP
    0.76
     wcześ
    0.75
     communists
    0.75
     zvlá
    0.75
    Activations Density 0.021%

    No Known Activations