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. 180
    Prev
    Next
    INDEX
    Explanations

    key and code events

    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
    träge
    -0.82
     poderia
    -0.81
    Fou
    -0.75
    Picasso
    -0.75
     Cheer
    -0.73
    paigns
    -0.73
    IMENTAL
    -0.72
    Extrait
    -0.72
    Leaving
    -0.72
    JAS
    -0.72
    POSITIVE LOGITS
     code
    0.94
    code
    0.93
     it
    0.84
     which
    0.80
     key
    0.79
    Code
    0.74
     utterly
    0.74
    CODE
    0.71
     char
    0.70
    repeat
    0.69
    Activations Density 0.025%

    No Known Activations