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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8351
    Prev
    Next
    INDEX
    Explanations

    character's story or traits

    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
     heroes
    -1.19
    邨
    -0.94
    ђа
    -0.94
    텝
    -0.93
    ::~
    -0.90
     герои
    -0.85
     heroine
    -0.84
     XXXVI
    -0.83
     argv
    -0.82
     יצ
    -0.82
    POSITIVE LOGITS
     backstory
    1.64
     interactions
    1.38
     story
    1.27
     motivation
    1.24
     origin
    1.22
     personality
    1.21
     actions
    1.21
     design
    1.16
     characteristics
    1.16
     character
    1.15
    Activations Density 0.022%

    No Known Activations