© 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
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 15282
    Prev
    Next
    INDEX
    Explanations

    knee airbag

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

    neon signs

    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_16_width_16k_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
    ebay
    0.64
    هِ
    0.62
    तम
    0.59
    ї
    0.57
    膿
    0.57
    বারের
    0.56
    чему
    0.55
     интересный
    0.55
    як
    0.54
     захворю
    0.54
    POSITIVE LOGITS
    是
    0.60
    3
    0.55
     idyllic
    0.54
    足够
    0.53
    </h3>
    0.53
     
    0.53
    4
    0.52
     cukup
    0.52
     jeruk
    0.52
     is
    0.52
    Activations Density 0.002%

    No Known Activations