© 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. 45462
    Prev
    Next
    INDEX
    Explanations

    Punctuation and code delimiters

    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
    Unless
    -0.92
     Unless
    -0.89
    дото
    -0.85
     Executes
    -0.84
    opold
    -0.84
    除非
    -0.84
     除
    -0.79
     adicionar
    -0.78
    ियन
    -0.77
     unless
    -0.77
    POSITIVE LOGITS
    ionales
    0.75
     castig
    0.75
     Duties
    0.72
    $=\
    0.72
    CAM
    0.72
    过来
    0.71
     Expectations
    0.69
     учё
    0.69
    根据
    0.69
    故事
    0.68
    Activations Density 0.001%

    No Known Activations