© 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. 26036
    Prev
    Next
    INDEX
    Explanations

    words following specific words

    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
     разных
    -1.63
     gotten
    -1.15
     legit
    -1.13
     будто
    -1.09
    为啥
    -1.09
     iliş
    -1.08
     novedades
    -1.08
     проє
    -1.06
    もあった
    -1.05
     nějak
    -1.04
    POSITIVE LOGITS
    Whilst
    1.29
     Whilst
    1.24
     TÉCN
    1.18
     whilst
    1.17
    ׇ
    1.10
    🤙
    1.05
    🏟
    1.02
     muß
    1.01
     pengantin
    1.01
    🌈
    0.99
    Activations Density 0.266%

    No Known Activations