© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25737
    Prev
    Next
    INDEX
    Explanations

    javascript dom manipulation

    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
    Acting
    -0.79
     tenure
    -0.76
     estrés
    -0.72
     къде
    -0.71
     Acting
    -0.71
     Hongrie
    -0.71
     кино
    -0.71
     répar
    -0.68
    一人で
    -0.68
     APPLY
    -0.67
    POSITIVE LOGITS
    attr
    1.41
    css
    1.40
    html
    1.26
    find
    1.23
     attr
    1.21
     css
    1.17
    prop
    1.11
     html
    1.08
    val
    1.04
     find
    0.98
    Activations Density 0.069%

    No Known Activations