© 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. 8573
    Prev
    Next
    INDEX
    Explanations

    extract randomness

    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
     ప్రారంభ
    0.46
     关闭
    0.44
     该
    0.43
    ટર
    0.41
     cramped
    0.41
    ियर
    0.41
     Же
    0.41
    rakt
    0.40
     开始
    0.40
    یدم
    0.40
    POSITIVE LOGITS
    isVisible
    0.49
    感情
    0.47
    and
    0.46
    มั่น
    0.46
    ങ്ക
    0.46
    года
    0.44
    после
    0.43
    Grady
    0.43
    噂
    0.42
     milik
    0.41
    Activations Density 0.012%

    No Known Activations