© 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. 134532
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
     típica
    0.40
     ഓര്‍
    0.39
     Smithsonian
    0.38
     Honors
    0.38
     própri
    0.38
     abiding
    0.38
    飭
    0.36
     ღ
    0.36
     فٹ
    0.36
     উপাদান
    0.36
    POSITIVE LOGITS
     कहर
    0.37
    ас
    0.37
    kových
    0.37
    acy
    0.37
     selten
    0.36
    nos
    0.35
    रों
    0.35
    olt
    0.35
    spectrum
    0.35
     sj
    0.35
    Activations Density 0.001%

    No Known Activations