© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23678
    Prev
    Next
    INDEX
    Explanations

    throughout or during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ：……
    -0.88
    以上です
    -0.86
     endless
    -0.83
     annual
    -0.82
     jähr
    -0.82
     одним
    -0.80
    ='';
    -0.79
     elettrico
    -0.77
    上次
    -0.76
     nơi
    -0.75
    POSITIVE LOGITS
     throughout
    8.25
    throughout
    6.28
    Throughout
    5.78
     Throughout
    5.69
     THRO
    3.98
    ตลอด
    3.55
     протягом
    3.38
     sepanjang
    3.30
     протяжении
    3.27
     durante
    3.06
    Activations Density 0.214%

    No Known Activations