© 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. 33374
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ℗
    -0.83
     customized
    -0.81
    cheers
    -0.78
     powietrza
    -0.77
     personalized
    -0.75
    ším
    -0.74
    &_
    -0.74
     kekerasan
    -0.74
     virtualization
    -0.73
    థ
    -0.73
    POSITIVE LOGITS
     Diary
    0.83
     العين
    0.81
    diferentes
    0.80
     SECRET
    0.79
     reklam
    0.76
    ⌫
    0.75
     WORDS
    0.75
    薄い
    0.75
     NEED
    0.74
    recrow
    0.74
    Activations Density 0.004%

    No Known Activations