© 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-65K
    7. 28312
    Prev
    Next
    INDEX
    Explanations

    related to descriptions or states

    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_65k_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
     болезнь
    0.45
     owning
    0.44
        
    0.43
     materi
    0.43
     crackers
    0.43
    дру
    0.43
    數
    0.43
     CLOS
    0.42
    ள்ளது
    0.42
    đồng
    0.42
    POSITIVE LOGITS
    活跃
    0.46
     İstifadə
    0.43
    LER
    0.41
    悱
    0.41
     ブラック
    0.41
    SuccessListener
    0.41
    oty
    0.40
    สดง
    0.40
    BleStatus
    0.40
    areti
    0.40
    Activations Density 0.006%

    No Known Activations