© 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. 186778
    Prev
    Next
    INDEX
    Explanations

    auditor certified

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

    how to describe quality and luxury

    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
     PRICE
    0.52
    ো
    0.50
     Problem
    0.48
     Ararat
    0.47
     Capitals
    0.46
     manipulations
    0.46
     BigDecimal
    0.45
     problém
    0.45
     PRICES
    0.45
    ্যাল
    0.44
    POSITIVE LOGITS
    일상
    0.50
     دهه
    0.50
    щем
    0.49
    embod
    0.47
     دوس
    0.46
     を
    0.46
    PhysRev
    0.46
     म्हणतात
    0.45
    exam
    0.44
     ее
    0.43
    Activations Density 0.000%

    No Known Activations