© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20172
    Prev
    Next
    INDEX
    Explanations

    understanding and clarity

    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
    漠
    0.42
    engkap
    0.42
    Jogador
    0.41
     năm
    0.40
     يمكن
    0.40
    ແລະ
    0.40
     completa
    0.39
    更能
    0.39
     động
    0.39
     dinámica
    0.39
    POSITIVE LOGITS
    ',\
    0.42
     vocals
    0.41
    CHECKS
    0.40
    pop
    0.40
    CriteriaUtils
    0.39
    %';
    0.39
     birch
    0.38
     pop
    0.37
     communication
    0.37
     Rajesh
    0.36
    Activations Density 0.001%

    No Known Activations