© 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. 84650
    Prev
    Next
    INDEX
    Explanations

    award ceremony, director, password

    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
     الرحمن
    -0.82
    diman
    -0.73
    Some
    -0.73
     ર
    -0.71
    ثار
    -0.71
     Vay
    -0.69
    Through
    -0.69
    WA
    -0.68
     ガー
    -0.68
    When
    -0.68
    POSITIVE LOGITS
    ätta
    0.85
    Lys
    0.82
    дравствуйте
    0.81
     Tweed
    0.79
     Lys
    0.78
     Weibo
    0.78
     netizens
    0.78
     righteousness
    0.76
    therin
    0.76
     infan
    0.74
    Activations Density 0.012%

    No Known Activations