© 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-65K
    7. 28293
    Prev
    Next
    INDEX
    Explanations

    special markers and phrases

    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
    मीर
    0.47
    ⊡
    0.47
     הת
    0.47
    衊
    0.46
    ਰ
    0.45
     ہمیشہ
    0.44
    𝐴
    0.44
    常に
    0.44
     ос
    0.42
    FRED
    0.42
    POSITIVE LOGITS
    ')",
    0.42
    cha
    0.41
    which
    0.39
    ಭಾಗ
    0.38
     Giang
    0.38
    োর্টের
    0.38
     which
    0.37
     aqueous
    0.37
     transporting
    0.37
    ogen
    0.36
    Activations Density 0.015%

    No Known Activations