© 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. 28961
    Prev
    Next
    INDEX
    Explanations

    public opinion and voters

    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
     such
    -1.30
     previously
    -1.30
     We
    -1.28
    riert
    -1.27
     utilizzare
    -1.27
    3
    -1.26
     realizzato
    -1.23
    Jeden
    -1.23
    фора
    -1.23
     シル
    -1.23
    POSITIVE LOGITS
    
    1.38
    breviations
    1.36
     wants
    1.23
    madeus
    1.23
     artisanal
    1.20
    则是
    1.17
    angering
    1.16
     understand
    1.14
    ⅽ
    1.14
    有两
    1.13
    Activations Density 0.054%

    No Known Activations