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. 8269
    Prev
    Next
    INDEX
    Explanations

    handwritten marks and annotations

    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
     kū
    -0.82
     email
    -0.80
    analog
    -0.79
    海报
    -0.79
    뱃
    -0.77
     poster
    -0.76
    ogni
    -0.75
    PostBack
    -0.74
     homage
    -0.73
    文案
    -0.73
    POSITIVE LOGITS
     pencil
    1.19
     handwriting
    1.18
     notations
    1.18
     circled
    1.18
     entries
    1.17
     spaces
    1.16
     annotations
    1.16
     doodles
    1.13
    Entries
    1.13
     corrections
    1.11
    Activations Density 0.024%

    No Known Activations