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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212382
    Prev
    Next
    INDEX
    Explanations

    building something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     일
    0.45
     intér
    0.43
    ሞች
    0.43
     Duma
    0.42
    哑
    0.42
    包括
    0.41
     एड
    0.41
    ዥ
    0.41
     stressors
    0.40
     employers
    0.39
    POSITIVE LOGITS
    ដូច្ន
    0.42
     ؛
    0.42
    টিয়ে
    0.41
    чения
    0.39
    anaan
    0.38
    itei
    0.38
     kemenangan
    0.38
    atini
    0.37
     θέση
    0.37
    öffentlichung
    0.36
    Activations Density 0.000%

    No Known Activations