© 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. 150122
    Prev
    Next
    INDEX
    Explanations

    real estate and devices

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

    gleaming, years, captured, fantasy, models, ads

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fearing
    0.53
     賞
    0.48
     Lobkovic
    0.47
     wavelength
    0.46
     ต้องการ
    0.46
     manipulated
    0.43
     বাজারে
    0.43
     destroyed
    0.42
     buttocks
    0.42
     وكان
    0.42
    POSITIVE LOGITS
    is
    0.52
    िस
    0.49
    ດ
    0.49
    养
    0.48
    isf
    0.47
    يس
    0.46
    Beef
    0.46
    alth
    0.46
    წყ
    0.46
    战略
    0.46
    Activations Density 0.000%

    No Known Activations