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. 8183
    Prev
    Next
    INDEX
    Explanations

    url scheme, host, path

    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
    becue
    -0.73
     metav
    -0.72
     القدم
    -0.68
     Robyn
    -0.68
     nám
    -0.67
    EU
    -0.67
    aderie
    -0.67
    𝖛
    -0.66
    新娘
    -0.66
    europe
    -0.65
    POSITIVE LOGITS
     scheme
    1.92
    scheme
    1.63
     Scheme
    1.62
    Scheme
    1.56
     host
    1.53
     schemes
    1.41
     SCHEME
    1.30
     authority
    1.30
     path
    1.27
     Schemes
    1.24
    Activations Density 0.036%

    No Known Activations