© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162739
    Prev
    Next
    INDEX
    Explanations

    cross-border improved stability donor touch

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

    description of adult activity

    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
     ઈ
    0.45
    -,
    0.44
     Boo
    0.44
     میدان
    0.42
    自觉
    0.42
     offence
    0.41
    -;
    0.41
    -
    0.41
     -,
    0.40
     of
    0.40
    POSITIVE LOGITS
     기본적인
    0.49
     chromium
    0.48
    щаем
    0.47
     rescaling
    0.45
     resizing
    0.45
    大多數
    0.45
     soln
    0.45
    ਾਨੂੰ
    0.44
     chrom
    0.44
     normalizing
    0.44
    Activations Density 0.000%

    No Known Activations