© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34695
    Prev
    Next
    INDEX
    Explanations

    admit that or admit to

    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
     he
    -2.05
     awful
    -1.95
                
    -1.88
     oh
    -1.80
     nehmen
    -1.77
    ll
    -1.77
     amassed
    -1.77
     $
    -1.75
     no
    -1.73
    神器
    -1.71
    POSITIVE LOGITS
     that
    2.00
     sağlay
    1.99
     sağlar
    1.98
    ably
    1.98
    状况
    1.95
    ㌘
    1.91
     ופ
    1.89
    
    1.87
    櫺
    1.82
    遢
    1.80
    Activations Density 0.013%

    No Known Activations