© 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. 10007
    Prev
    Next
    INDEX
    Explanations

    quoted and delimited phrases

    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
     '
    -4.31
    ',
    -3.22
    潆
    -2.81
     crafty
    -2.70
     ('
    -2.64
    ..."
    -2.63
    ،
    -2.59
     estábamos
    -2.56
     doesnt
    -2.48
     związane
    -2.39
    POSITIVE LOGITS
    塒
    2.92
    .
    2.58
    怱
    2.52
    猻
    2.50
    籥
    2.36
    which
    2.31
    㤵
    2.28
    屨
    2.28
     THAN
    2.28
    mpagne
    2.28
    Activations Density 0.001%

    No Known Activations