© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11005
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and abbreviations

    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
    {
    -1.63
    ers
    -1.59
     our
    -1.58
     was
    -1.51
    :");
    -1.39
    𞤢
    -1.38
     us
    -1.34
    */
    -1.33
     anderes
    -1.33
     më
    -1.32
    POSITIVE LOGITS
    aimeJ
    1.45
     profite
    1.42
    ことも
    1.42
    roidery
    1.39
     estadounidenses
    1.38
    роваться
    1.33
    owatt
    1.32
    Depending
    1.30
    閿
    1.30
     conversely
    1.29
    Activations Density 0.008%

    No Known Activations