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. 8024
    Prev
    Next
    INDEX
    Explanations

    script tag attributes

    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
     css
    -0.89
     indoc
    -0.89
    atrième
    -0.89
     Rigid
    -0.84
     Escor
    -0.84
     styles
    -0.83
     Vapour
    -0.82
     STYLES
    -0.80
    Crow
    -0.80
     MEANS
    -0.80
    POSITIVE LOGITS
     charset
    1.23
     type
    1.19
     async
    1.03
    charset
    1.02
     Type
    1.01
     language
    1.00
    type
    0.98
     defer
    0.89
     Language
    0.88
     tipo
    0.88
    Activations Density 0.024%

    No Known Activations