© 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. 10-GEMMASCOPE-RES-131K
    7. 100948
    Prev
    Next
    INDEX
    Explanations

    cashier, teller, register

    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
    ᠂
    -2.64
     cynical
    -2.48
    躄
    -2.47
     sollte
    -2.44
     brazen
    -2.38
    憷
    -2.36
    ☫
    -2.34
     indulge
    -2.31
     ซึ่ง
    -2.28
     astute
    -2.27
    POSITIVE LOGITS
                    
    2.22
    ные
    2.13
                             
    2.09
                                
    2.08
     ponts
    1.91
    kenal
    1.91
        
    1.89
               
    1.85
    ми
    1.84
    From
    1.84
    Activations Density 0.002%

    No Known Activations