© 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. 34-GEMMASCOPE-RES-131K
    7. 60055
    Prev
    Next
    INDEX
    Explanations

    in person

    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_34/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
     работников
    -0.81
                                 
    -0.78
    ε
    -0.75
    क्
    -0.75
    ynth
    -0.74
                      
    -0.73
                                  
    -0.73
    ཏ
    -0.70
    intra
    -0.69
    aryl
    -0.69
    POSITIVE LOGITS
     person
    5.31
    person
    3.98
    Person
    3.69
     Person
    3.47
     PERSON
    3.38
    PERSON
    3.13
     شخص
    2.80
     pessoa
    2.69
     persoon
    2.66
     személy
    2.63
    Activations Density 0.040%

    No Known Activations