© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5844
    Prev
    Next
    INDEX
    Explanations

    formatting and lists

    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_16k_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
    ʦ
    0.39
    ಲಿಯ
    0.37
     ליי
    0.37
    צ
    0.36
     č
    0.35
    푐
    0.35
     चालक
    0.34
    ɗ
    0.34
    바
    0.33
    äk
    0.33
    POSITIVE LOGITS
     informée
    0.37
    غيرة
    0.37
     viciss
    0.36
     Время
    0.35
    বাল
    0.35
     plurality
    0.34
     अद्भुत
    0.34
    বিদেশ
    0.34
    trending
    0.34
    jResponse
    0.34
    Activations Density 0.689%

    No Known Activations