© 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. 74000
    Prev
    Next
    INDEX
    Explanations

    Garden boat, burning passion, pay the, assisted you, through this, kids, citing Kavanaugh

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

    programming, math, and services

    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
     by
    0.52
     timeless
    0.47
     parse
    0.46
     progres
    0.46
     for
    0.45
     texto
    0.45
    3
    0.45
    جه
    0.45
    program
    0.44
     obligaciones
    0.43
    POSITIVE LOGITS
    Ɲ
    0.50
    フライ
    0.50
     そこ
    0.48
    CreateModel
    0.47
    橦
    0.47
     ਇਹ
    0.47
    RatingDiff
    0.46
     സെക്രട്ടറി
    0.46
    ブ
    0.46
     সচিব
    0.46
    Activations Density 0.000%

    No Known Activations