© 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. 75143
    Prev
    Next
    INDEX
    Explanations

    starting or beginning

    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
     now
    -1.62
     subsequently
    -1.35
     then
    -1.35
     ブレスレット
    -1.07
    now
    -1.07
     теперь
    -1.03
    Now
    -1.02
     sekarang
    -1.01
    現在は
    -1.00
    さらに
    -0.99
    POSITIVE LOGITS
     initially
    2.03
     initial
    1.95
     ابتدا
    1.85
     first
    1.84
     early
    1.70
     inicialmente
    1.68
    一開始
    1.63
    нача
    1.63
    一开始
    1.63
     zunächst
    1.62
    Activations Density 0.033%

    No Known Activations