© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45241
    Prev
    Next
    INDEX
    Explanations

    Hebrew and Arabic texts

    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
     that
    -2.31
    ”、“
    -1.99
     /
    -1.89
     >
    -1.84
     –
    -1.84
     &&
    -1.83
     in
    -1.78
    //
    -1.77
     {
    -1.71
     including
    -1.71
    POSITIVE LOGITS
    쐈
    1.88
     be
    1.84
    indeed
    1.79
    samt
    1.78
    wakili
    1.73
    屨
    1.73
    焿
    1.70
    涐
    1.65
    ῞
    1.65
     IBOutlet
    1.65
    Activations Density 0.003%

    No Known Activations