© 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-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 55971
    Prev
    Next
    INDEX
    Explanations

    linguistic structure setup

    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
     Zanu
    0.48
    隱
    0.48
    鈑
    0.47
     Хер
    0.47
    |");
    0.46
     হুগ
    0.45
     thous
    0.45
    詑
    0.45
     impec
    0.44
     |”
    0.44
    POSITIVE LOGITS
    tej
    0.43
    ist
    0.42
    痴
    0.41
    ksi
    0.40
    孖
    0.40
     preparação
    0.39
     surgery
    0.39
    运
    0.38
    
    0.38
    sten
    0.37
    Activations Density 0.002%

    No Known Activations