© 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. 48194
    Prev
    Next
    INDEX
    Explanations

    programming and web development

    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
    unduh
    -1.67
     allerlei
    -1.55
     vélos
    -1.52
    我们
    -1.52
    Díky
    -1.49
    Válasz
    -1.49
    عنوان
    -1.47
    ২
    -1.41
    我們
    -1.40
    Whilst
    -1.40
    POSITIVE LOGITS
     in
    1.45
     with
    1.34
     this
    1.27
     !!!
    1.23
     always
    1.23
     maybe
    1.23
     like
    1.21
     remain
    1.20
     now
    1.20
     many
    1.19
    Activations Density 1.064%

    No Known Activations