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

    Neuronpedia

    Jacobian LensNEW
    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. 47306
    Prev
    Next
    INDEX
    Explanations

    comfort, survival, blockchain, established

    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
    Ẻ
    0.57
     that
    0.51
     to
    0.50
     sweat
    0.45
     và
    0.45
          
    0.44
         
    0.44
     proliferation
    0.43
     টিভির
    0.43
     regimens
    0.43
    POSITIVE LOGITS
    يد
    0.53
    x
    0.52
    チーム
    0.49
    })=\
    0.48
    歐
    0.47
    ቖ
    0.46
    टीम
    0.46
    淺
    0.46
    浅
    0.46
    мов
    0.46
    Activations Density 0.004%

    No Known Activations