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. 8017
    Prev
    Next
    INDEX
    Explanations

    up to

    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
     capucha
    -0.98
     maleta
    -0.96
     manicura
    -0.94
     manchas
    -0.91
     artesanía
    -0.90
    WireFormat
    -0.88
     felpa
    -0.88
    جویان
    -0.88
     rayas
    -0.88
    helial
    -0.88
    POSITIVE LOGITS
     to
    4.41
     đến
    1.27
    ถึง
    1.06
    到
    1.05
     than
    0.99
     līdz
    0.94
    為に
    0.91
    至
    0.88
     till
    0.87
     stroking
    0.87
    Activations Density 0.011%

    No Known Activations