© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54459
    Prev
    Next
    INDEX
    Explanations

    conditional logic or null checks

    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_22/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
    わかります
    -0.82
    阉
    -0.81
    occuper
    -0.79
    玫
    -0.79
    onné
    -0.76
    わかった
    -0.76
    akkan
    -0.74
    isse
    -0.72
    亚马逊
    -0.72
    都需要
    -0.72
    POSITIVE LOGITS
     नहीं
    1.11
    /***/
    1.07
    默认
    1.00
    沒有
    0.98
    ไม่มี
    0.97
     no
    0.96
     değil
    0.94
     δεν
    0.93
    为空
    0.90
    没有
    0.90
    Activations Density 0.006%

    No Known Activations