© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23168
    Prev
    Next
    INDEX
    Explanations

    wondrous times

    np_acts-logits-general · gemini-2.5-flash-lite

    gradually increasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सर्वप्रथम
    0.44
     лично
    0.43
     εκεί
    0.42
    defaultValue
    0.42
     immédiatement
    0.41
    reci
    0.41
    ग्राह
    0.41
     ઘરે
    0.41
     चार्
    0.40
    igura
    0.40
    POSITIVE LOGITS
     점점
    0.84
    越來越
    0.81
    どんどん
    0.79
    越来越多
    0.76
    真是
    0.74
    왤
    0.71
    Seems
    0.71
    越来越多的
    0.71
    越来越
    0.70
    不斷
    0.70
    Activations Density 0.209%

    No Known Activations