© 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. 85063
    Prev
    Next
    INDEX
    Explanations

    homelessness multicultural society

    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
    ᕱ
    -2.94
    ⪧
    -2.64
    摃
    -2.64
    鐽
    -2.58
    ★☆
    -2.56
    
    -2.56
    ⡱
    -2.50
     nettoyer
    -2.47
     hals
    -2.47
    彀
    -2.45
    POSITIVE LOGITS
     {
    2.89
     \
    2.78
     -
    2.78
    .,
    2.67
     Personally
    2.63
     About
    2.59
     Indeed
    2.48
    ();
    2.41
    遢
    2.39
     Similarly
    2.38
    Activations Density 0.005%

    No Known Activations