© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 140070
    Prev
    Next
    INDEX
    Explanations

    supporters hit, blogger must

    np_acts-logits-general · gemini-2.5-flash-lite

    legitimate Windows license or key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     были
    0.55
    𝚜
    0.55
    бург
    0.54
     étaient
    0.52
    ANGMAR
    0.52
     były
    0.51
     다양
    0.51
     была
    0.50
     були
    0.50
     घरेलू
    0.50
    POSITIVE LOGITS
     destinations
    0.48
    ق
    0.46
     configurations
    0.43
     benchmarks
    0.42
     vocation
    0.42
    鑰
    0.42
    澧
    0.42
     prerequisites
    0.41
    倝
    0.41
     modes
    0.41
    Activations Density 0.001%

    No Known Activations