© 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. 22-GEMMASCOPE-RES-131K
    7. 386
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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_22/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
     tragé
    -1.16
     condicionado
    -1.16
     aantal
    -1.10
     hours
    -1.09
     Jogos
    -1.06
    FundMe
    -1.06
    ｪ
    -1.05
    média
    -1.05
     perdeu
    -1.05
     langu
    -1.04
    POSITIVE LOGITS
    剛好
    1.15
    そういった
    1.05
    否认
    1.05
    噁
    1.02
    niers
    1.02
    认真的
    1.00
     rentrer
    0.99
     ""
    0.98
    粉絲
    0.96
    干脆
    0.96
    Activations Density 0.021%

    No Known Activations