© 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. 76194
    Prev
    Next
    INDEX
    Explanations

    significant cognitive impairment

    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
    handle
    0.45
    customer
    0.44
    wen
    0.43
    hbs
    0.42
    ↵
    0.42
    others
    0.41
     modify
    0.41
     tanah
    0.40
    show
    0.39
    wf
    0.39
    POSITIVE LOGITS
     institutes
    0.45
     প্রবাসী
    0.45
     precludes
    0.43
     ఫో
    0.41
    বাদে
    0.41
     Compounds
    0.41
     Sü
    0.39
     Nis
    0.38
     cyclo
    0.38
    飪
    0.38
    Activations Density 0.000%

    No Known Activations