© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    ሮች
    0.41
    នឹង
    0.37
     toeg
    0.36
    anea
    0.35
    Wrap
    0.34
    Ely
    0.34
     forego
    0.34
    └──
    0.34
    ಲೂ
    0.34
     अनेक
    0.33
    POSITIVE LOGITS
    三个
    0.49
     তিনজন
    0.49
     drei
    0.47
    three
    0.45
     два
    0.44
     তিনটি
    0.42
    三個
    0.42
     three
    0.42
     ê
    0.41
     দুইজন
    0.41
    Activations Density 0.239%

    No Known Activations