© 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. 190891
    Prev
    Next
    INDEX
    Explanations

    open source community contributions

    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
    Վ
    0.40
    INTRESOURCE
    0.40
     MINISTER
    0.38
    GRID
    0.38
     модуля
    0.38
     বিন্দু
    0.38
    unuh
    0.37
    levi
    0.37
    ๅ
    0.37
     teclas
    0.37
    POSITIVE LOGITS
     overpowered
    0.41
     shop
    0.40
     come
    0.40
    shop
    0.39
     pol
    0.38
     avoid
    0.37
     red
    0.37
    Stopped
    0.37
     slow
    0.36
     aján
    0.35
    Activations Density 0.008%

    No Known Activations