© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8999
    Prev
    Next
    INDEX
    Explanations

    code and web development syntax

    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_65k_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
     perchè
    0.56
     alot
    0.50
     সম্পূর্ন
    0.50
    ﮧ
    0.46
    出来る
    0.46
     skall
    0.45
     বেশী
    0.44
    …..
    0.42
     dibawah
    0.42
     আক্রমন
    0.41
    POSITIVE LOGITS
     그다음에
    0.44
     به‌عنوان
    0.42
    ↵
    0.38
     Nonprofit
    0.36
     Mei
    0.36
     Trust
    0.35
     policym
    0.35
    ຸກ
    0.35
    筚
    0.35
     Men
    0.35
    Activations Density 0.045%

    No Known Activations