© 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. 46621
    Prev
    Next
    INDEX
    Explanations

    dramatic descriptions

    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
    是一个
    0.44
    τός
    0.42
    ọ
    0.41
    为什么
    0.40
     cannot
    0.39
    一个月
    0.39
    는
    0.39
    苌
    0.39
    র্ন
    0.39
     dosen
    0.39
    POSITIVE LOGITS
    퍽
    0.48
    結論
    0.44
     {\
    0.43
     correspondingly
    0.40
     explo
    0.40
    錯
    0.39
    patri
    0.38
    意義
    0.38
    uerre
    0.38
     equivalently
    0.38
    Activations Density 0.001%

    No Known Activations