© 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. 76026
    Prev
    Next
    INDEX
    Explanations

    numbers or labels followed by punctuation

    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
    endalikan
    -1.05
     considerare
    -0.99
    álva
    -0.94
     ricas
    -0.94
     modificare
    -0.93
    当我
    -0.92
     Whenever
    -0.92
    AxisAlignment
    -0.92
     cortinas
    -0.91
     kerjasama
    -0.91
    POSITIVE LOGITS
     to
    2.95
     and
    2.00
     až
    1.85
    到
    1.79
     onwards
    1.70
     hingga
    1.70
    -$
    1.67
     đến
    1.52
    至
    1.52
     \&
    1.51
    Activations Density 0.237%

    No Known Activations