© 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. 143281
    Prev
    Next
    INDEX
    Explanations

    Google Ads campaign

    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
    ม
    0.48
    लियों
    0.48
     Organizations
    0.46
     Triangle
    0.46
     moisturizing
    0.46
     airplanes
    0.44
     gond
    0.44
    צל
    0.44
    
    0.43
     চিন্ত
    0.43
    POSITIVE LOGITS
     misma
    0.51
     drugi
    0.43
    헹
    0.42
    prime
    0.42
    u
    0.42
    Ă
    0.42
     동일
    0.41
    做到
    0.40
    in
    0.39
     четы
    0.39
    Activations Density 0.007%

    No Known Activations