© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25388
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and liability

    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
    ίας
    0.42
     fraudulently
    0.40
    ໌
    0.38
     ordinances
    0.36
    不然
    0.35
     العزيز
    0.35
     apparently
    0.35
    ၊
    0.35
    Wnd
    0.35
    ដើម្បី
    0.35
    POSITIVE LOGITS
     College
    0.47
     Blanche
    0.42
     COLLEGE
    0.38
     But
    0.38
     Dep
    0.37
     Break
    0.37
     it
    0.37
     nothing
    0.36
     Election
    0.36
    College
    0.36
    Activations Density 0.002%

    No Known Activations