© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    hope this

    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
    ທ່ານ
    0.53
    ร
    0.52
    จะ
    0.51
    轉換
    0.50
    ไป
    0.50
    能夠
    0.50
    會有
    0.50
    ยัง
    0.49
    ยังมี
    0.49
    會
    0.49
    POSITIVE LOGITS
     to
    0.52
    iloc
    0.48
     betont
    0.46
     facto
    0.45
     (!)
    0.45
    juv
    0.45
     makes
    0.43
     seems
    0.42
     emphasizes
    0.41
    tert
    0.41
    Activations Density 0.005%

    No Known Activations