© 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. 247024
    Prev
    Next
    INDEX
    Explanations

    measurements, constraint, festival

    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
     Lovely
    0.47
    ที่คุณ
    0.45
    SpringMVCProject
    0.45
    綴
    0.45
    ूटूथ
    0.44
    โด
    0.44
    ですよね
    0.44
     पसंदीदा
    0.44
     นี่
    0.43
    ᒎ
    0.43
    POSITIVE LOGITS
    HIGH
    0.49
    ب
    0.48
     nač
    0.46
     hiring
    0.45
    дини
    0.45
     grunds
    0.43
    фри
    0.43
    IS
    0.43
    ס
    0.43
    SCHEDULE
    0.42
    Activations Density 0.001%

    No Known Activations