© 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. 10-GEMMASCOPE-RES-131K
    7. 65621
    Prev
    Next
    INDEX
    Explanations

    lodging and shelters

    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_10/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
    罽
    -2.88
    葑
    -2.69
    鸲
    -2.58
    瑨
    -2.52
    ang
    -2.44
    潆
    -2.44
    扃
    -2.27
    辔
    -2.20
    ญี่ป
    -2.20
    
    -2.19
    POSITIVE LOGITS
    ’
    2.38
     '
    2.14
    ,”
    2.11
    」
    2.09
    ><
    2.09
    )
    2.06
    缎
    2.02
    We
    2.00
    It
    1.96
    如果
    1.96
    Activations Density 0.002%

    No Known Activations