© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48380
    Prev
    Next
    INDEX
    Explanations

    quotes followed by names

    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
     bzw
    -0.91
    fehlungen
    -0.88
     でも
    -0.85
    葱
    -0.82
     entró
    -0.80
    Ƿ
    -0.79
     two
    -0.79
    hoten
    -0.79
    。。。。
    -0.79
     மூ
    -0.79
    POSITIVE LOGITS
    quote
    1.66
     quoted
    1.66
     quote
    1.64
    Quote
    1.61
     Quote
    1.54
    quoted
    1.47
     quotation
    1.47
    Quoted
    1.45
     quotes
    1.41
     Quoted
    1.41
    Activations Density 0.022%

    No Known Activations