© 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. 34-GEMMASCOPE-RES-131K
    7. 92728
    Prev
    Next
    INDEX
    Explanations

    words ending in ail

    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
    ioneers
    -0.84
     eleições
    -0.80
    したいと思います
    -0.77
     道
    -0.75
    一场
    -0.75
    ਾ
    -0.74
     octombrie
    -0.73
    넌
    -0.73
    監視
    -0.72
    вини
    -0.71
    POSITIVE LOGITS
    riscoll
    0.82
    ings
    0.81
     Enhance
    0.79
    ors
    0.79
    illon
    0.76
    鎌
    0.75
     progn
    0.75
    ored
    0.74
    .!
    0.73
     obstante
    0.73
    Activations Density 0.021%

    No Known Activations