© 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. 10-GEMMASCOPE-RES-131K
    7. 12168
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_10/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
     mereka
    -2.02
     zvuky
    -1.99
    왁
    -1.92
     solace
    -1.80
    retario
    -1.69
     trouvez
    -1.68
     aching
    -1.66
    ïdes
    -1.66
     -
    -1.64
     disait
    -1.64
    POSITIVE LOGITS
     \
    1.93
    
    1.79
     our
    1.77
     \
    1.73
     {
    1.70
     et
    1.68
     Strecken
    1.65
    $,
    1.63
     on
    1.59
    橚
    1.58
    Activations Density 0.011%

    No Known Activations