© 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. 250348
    Prev
    Next
    INDEX
    Explanations

    availability, calendar, flowers, time, tip, prediction

    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
    ν
    0.48
    田
    0.46
    я
    0.45
     Tash
    0.44
    кы
    0.44
    ს
    0.43
    ],[
    0.43
     пишу
    0.43
     মেজর
    0.43
    ве
    0.42
    POSITIVE LOGITS
     subcellular
    0.47
     sought
    0.47
     saiu
    0.47
     setResult
    0.46
     (_,
    0.44
     extend
    0.44
     especies
    0.44
     Sought
    0.44
    ىڭ
    0.43
    ွာ
    0.43
    Activations Density 0.001%

    No Known Activations