© 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-262K
    7. 38269
    Prev
    Next
    INDEX
    Explanations

    list items or code blocks

    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_262k_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
    原来的
    0.50
    推广
    0.46
     complicated
    0.45
     sequ
    0.44
     malignancy
    0.42
    ✧
    0.42
    动作
    0.42
    还是要
    0.42
    ಮಾಣ
    0.41
    퀀
    0.41
    POSITIVE LOGITS
     intéressant
    0.49
    й
    0.48
    р
    0.47
     prairies
    0.46
     firsthand
    0.44
     és
    0.43
     ô
    0.43
     Aberdeen
    0.43
    それぞれ
    0.43
    ुरु
    0.42
    Activations Density 0.002%

    No Known Activations