© 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. 21765
    Prev
    Next
    INDEX
    Explanations

    unit conversions, lists, or specific entities

    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
    
    -1.67
     
    -1.66
     Puede
    -1.55
                    
    -1.51
     feiert
    -1.47
     None
    -1.44
    ༔
    -1.43
    ਲ਼
    -1.43
    </
    -1.43
     l
    -1.43
    POSITIVE LOGITS
    注意事
    1.98
    Книга
    1.72
    饜
    1.66
    Akhir
    1.59
    end
    1.55
    捽
    1.55
     obicei
    1.54
    žite
    1.52
    ämie
    1.52
    ⭏
    1.49
    Activations Density 0.002%

    No Known Activations