© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11915
    Prev
    Next
    INDEX
    Explanations

    sample

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

    analysis of samples

    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
    动画
    0.41
     হুমকির
    0.41
    ദ്
    0.40
    باد
    0.38
     frmt
    0.37
    ബൈ
    0.37
    彤
    0.36
    坞
    0.36
    動畫
    0.36
     restoring
    0.35
    POSITIVE LOGITS
     samples
    2.56
     Samples
    2.38
    samples
    2.34
    Samples
    2.30
     sample
    2.17
    样本
    2.13
     sampel
    2.13
    サンプル
    2.09
    样品
    2.06
     échantillons
    2.06
    Activations Density 0.325%

    No Known Activations