© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10927
    Prev
    Next
    INDEX
    Explanations

    increases and decreases

    np_acts-logits-general · gemini-2.5-flash-lite

    body composition and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     developmentally
    0.47
     climático
    0.45
    闱
    0.44
    Israeli
    0.42
    信号
    0.41
    amana
    0.40
    Diabetes
    0.40
    ંટ
    0.40
    筛选
    0.39
    筛
    0.39
    POSITIVE LOGITS
    total
    0.64
     total
    0.62
     Total
    0.61
     TOTAL
    0.57
    Total
    0.54
     mean
    0.53
    総
    0.51
    mean
    0.50
    總
    0.48
     гре
    0.47
    Activations Density 0.236%

    No Known Activations