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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16813
    Prev
    Next
    INDEX
    Explanations

    reporting specific details

    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_31_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
     tuttavia
    0.45
     Mereka
    0.38
    他们的
    0.37
     آنها
    0.37
     آن‌ها
    0.37
    ۷
    0.37
    شان
    0.37
    ęcie
    0.36
     onlar
    0.35
    <unused338>
    0.34
    POSITIVE LOGITS
     warrantless
    0.57
     federally
    0.51
     securities
    0.51
     pursuant
    0.50
     borrowers
    0.47
     lawful
    0.47
     authorizes
    0.47
     administers
    0.46
     rental
    0.45
     amendment
    0.45
    Activations Density 0.000%

    No Known Activations