© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28886
    Prev
    Next
    INDEX
    Explanations

    Interactive Brokers API

    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
    Supreme
    0.45
    src
    0.43
    Scale
    0.43
    Justice
    0.41
     जस्टिस
    0.40
    <?
    0.39
    graphicx
    0.39
    
    0.38
     scale
    0.38
    ВС
    0.38
    POSITIVE LOGITS
     charitable
    0.51
     Charitable
    0.46
     redeeming
    0.43
     charities
    0.41
     Saratoga
    0.40
    ماية
    0.38
     Greenwich
    0.38
     redemption
    0.37
     charity
    0.37
     пись
    0.37
    Activations Density 0.002%

    No Known Activations