© 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. 14495
    Prev
    Next
    INDEX
    Explanations

    examples of how things work

    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
    Increased
    0.45
    ズ
    0.45
    сты
    0.43
    岧
    0.43
     titrated
    0.42
    𝐖
    0.41
    Additionally
    0.41
    출
    0.41
    Though
    0.41
    Hyper
    0.41
    POSITIVE LOGITS
    最重要的
    0.44
     Practice
    0.43
     گی۔
    0.42
    man
    0.41
    est
    0.41
    io
    0.41
    glob
    0.41
     ফি
    0.40
    enig
    0.39
     遅
    0.39
    Activations Density 0.015%

    No Known Activations