© 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. 4293
    Prev
    Next
    INDEX
    Explanations

    especially

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

    proportionally more

    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
    ர்ந்து
    0.34
     राज्यातील
    0.34
    ங்கிய
    0.32
     ಮೂಲ
    0.32
    צוני
    0.32
     nació
    0.31
     française
    0.31
    4
    0.31
    强大
    0.30
     asum
    0.30
    POSITIVE LOGITS
    特に
    0.55
     особенно
    0.52
     더욱
    0.50
     especially
    0.49
    更是
    0.49
    の場合は
    0.49
     besonders
    0.49
     особливо
    0.49
    場合は
    0.48
     특히
    0.48
    Activations Density 0.283%

    No Known Activations