© 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. 55889
    Prev
    Next
    INDEX
    Explanations

    still or remain

    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
     already
    -2.50
     вже
    -1.95
    Already
    -1.95
     уже
    -1.92
     Already
    -1.77
    ALREADY
    -1.77
     כבר
    -1.70
    already
    -1.70
     già
    -1.67
     bereits
    -1.63
    POSITIVE LOGITS
     still
    1.70
     masih
    1.60
     ยัง
    1.58
    仍
    1.55
     remain
    1.52
    依然
    1.48
     remains
    1.41
     vẫn
    1.41
    still
    1.38
     продолжа
    1.37
    Activations Density 0.086%

    No Known Activations