© 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. 10-GEMMASCOPE-RES-131K
    7. 47802
    Prev
    Next
    INDEX
    Explanations

    how to do something

    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_10/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
     заявил
    -1.55
    嘮
    -1.52
    怎么了
    -1.50
    彼らの
    -1.48
    还有什么
    -1.48
    最后由
    -1.42
     drôle
    -1.41
    Více
    -1.39
    网红
    -1.39
     soledad
    -1.38
    POSITIVE LOGITS
     of
    2.09
    他
    1.81
     but
    1.68
      
    1.63
     इसके
    1.60
    вери
    1.55
     This
    1.53
     هذا
    1.52
     this
    1.48
    this
    1.47
    Activations Density 0.019%

    No Known Activations