© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11762
    Prev
    Next
    INDEX
    Explanations

    ***

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    い
    0.69
     bús
    0.64
    ل
    0.63
    ב
    0.59
    อ
    0.57
    尔
    0.57
    ul
    0.54
     táct
    0.54
     lié
    0.52
    น
    0.52
    POSITIVE LOGITS
     രീതി
    0.67
    
    0.67
     Brings
    0.65
     Lithium
    0.64
    しょう
    0.62
     використання
    0.62
    tv
    0.61
    ்சை
    0.61
     Mounting
    0.60
     Shoulder
    0.60
    Activations Density 0.144%

    No Known Activations