Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8733
    Prev
    Next
    INDEX
    Explanations

    changing and evolving

    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
    込ま
    -0.73
    均匀
    -0.72
    jau
    -0.72
    openha
    -0.70
    springboot
    -0.70
    ()=>{
    -0.70
    ské
    -0.69
    친
    -0.69
    ぶりの
    -0.69
    ündigen
    -0.69
    POSITIVE LOGITS
     changing
    5.38
    changing
    4.63
    Changing
    4.34
     Changing
    4.19
     changes
    3.89
     changed
    3.70
     evolving
    3.61
     zmienia
    3.45
     change
    3.44
    changes
    3.30
    Activations Density 0.251%

    No Known Activations