© 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. 245984
    Prev
    Next
    INDEX
    Explanations

    circumstances, shortages, times, activate, champion

    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
    ัก
    0.42
    蹺
    0.41
    ov
    0.40
    s
    0.40
     tomorrow
    0.39
    檢查
    0.39
    o
    0.39
     Modulation
    0.38
    釆
    0.38
    સ
    0.38
    POSITIVE LOGITS
     епи
    0.52
     యొక్క
    0.51
    larınız
    0.50
     EXPL
    0.50
     aşağı
    0.49
     ඔවුන්
    0.49
     întâ
    0.49
     bağı
    0.48
    崭
    0.48
     фанта
    0.48
    Activations Density 0.001%

    No Known Activations