© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32890
    Prev
    Next
    INDEX
    Explanations

    don't forget to hide actions

    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_40_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
     দেখিলাম
    0.46
     GENERAL
    0.43
     мастеров
    0.43
     yǒu
    0.41
    国内外
    0.41
    worldly
    0.41
     옛
    0.40
     তপ
    0.40
     साध
    0.40
     livelihood
    0.39
    POSITIVE LOGITS
    那种
    0.50
    表情
    0.50
    反應
    0.49
    現在
    0.49
    登場
    0.47
     reaction
    0.46
    ██
    0.46
    出现在
    0.46
    揍
    0.46
    反应
    0.45
    Activations Density 0.001%

    No Known Activations