© 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. 38674
    Prev
    Next
    INDEX
    Explanations

    São Jorge Castle

    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
    ata
    0.45
     induce
    0.44
    轫
    0.44
    闌
    0.43
     defies
    0.43
     disreg
    0.43
    牪
    0.42
    APPED
    0.42
     Leib
    0.41
    Defs
    0.41
    POSITIVE LOGITS
    جل
    0.54
    ج
    0.47
    밀
    0.46
    งาน
    0.46
    カ
    0.46
    перы
    0.46
     système
    0.45
    میل
    0.45
    مه
    0.45
     electoral
    0.45
    Activations Density 0.002%

    No Known Activations