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. 8103
    Prev
    Next
    INDEX
    Explanations

    android xml code

    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
    !(
    -1.25
    !(
    -1.16
     even
    -1.15
    ! 
    -1.14
    ~。
    -1.10
    …!
    -1.09
     one
    -1.09
     because
    -1.08
    独特
    -1.08
     stellar
    -1.07
    POSITIVE LOGITS
     dreary
    1.30
     delightfully
    1.26
     этих
    1.24
     essas
    1.23
     boister
    1.23
     ™
    1.18
     AMAZING
    1.18
     predominantly
    1.18
    きち
    1.16
    鶫
    1.15
    Activations Density 0.003%

    No Known Activations