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. 8186
    Prev
    Next
    INDEX
    Explanations

    image, achievements, feelings, moving objects

    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
     nuage
    -0.96
    HAIR
    -0.85
    Lak
    -0.84
    珧
    -0.83
     Hickory
    -0.83
     италья
    -0.82
    vah
    -0.81
    ńska
    -0.80
     procé
    -0.80
    Показать
    -0.80
    POSITIVE LOGITS
     image
    1.09
     specifications
    1.00
     excellent
    0.96
     characteristics
    0.95
     feelings
    0.94
     important
    0.93
     evaluation
    0.91
     mysterious
    0.91
     results
    0.91
     their
    0.89
    Activations Density 0.137%

    No Known Activations