© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2066
    Prev
    Next
    INDEX
    Explanations

    Starting

    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_16_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
     với
    0.51
    0.43
     dengan
    0.40
    ità
    0.39
     मुख्य
    0.39
    ，
    0.38
     από
    0.38
    ência
    0.37
     ہے
    0.37
    ，“
    0.37
    POSITIVE LOGITS
    1
    0.39
    Y
    0.39
     Risks
    0.37
    WS
    0.36
    ו
    0.36
     Bldg
    0.36
     কিন্ত
    0.35
    യും
    0.34
    2
    0.34
    ‌ی
    0.34
    Activations Density 0.005%

    No Known Activations