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. 177
    Prev
    Next
    INDEX
    Explanations

    Bloody followed by Marys or Spear

    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
    urface
    -0.82
     sacar
    -0.78
     yogurt
    -0.77
    ACADEM
    -0.76
    äischen
    -0.75
     evrops
    -0.73
     Lio
    -0.73
    ilion
    -0.72
    KERNEL
    -0.72
    šu
    -0.72
    POSITIVE LOGITS
     Bloody
    2.25
    Bloody
    1.80
     bloody
    1.74
    bloody
    1.32
     tomato
    1.10
     hair
    1.08
    Hair
    1.05
     celery
    1.00
     Hair
    0.98
    Tomato
    0.98
    Activations Density 0.011%

    No Known Activations