© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73217
    Prev
    Next
    INDEX
    Explanations

    confirm end

    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
    },
    -2.95
     You
    -2.91
     The
    -2.80
    水晶
    -2.73
     essas
    -2.63
     anche
    -2.59
     ``
    -2.56
    蹰
    -2.56
     semej
    -2.53
     we
    -2.50
    POSITIVE LOGITS
     イラストレーション
    3.59
    
    3.20
     rosse
    3.08
    鹟
    3.05
    喼
    2.95
     felpa
    2.88
    錞
    2.84
    It
    2.77
     polie
    2.72
     火鍋
    2.72
    Activations Density 0.009%

    No Known Activations