© 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. 58850
    Prev
    Next
    INDEX
    Explanations

    specific token followed by common sequence

    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
    」
    -3.08
    ers
    -2.72
     {
    -2.69
    ꜆
    -2.69
    with
    -2.61
     avec
    -2.53
    ⡑
    -2.52
    勦
    -2.45
    ti
    -2.42
    [
    -2.38
    POSITIVE LOGITS
    ization
    2.73
    袛
    2.73
    鲣
    2.66
    呖
    2.64
    珦
    2.53
    緜
    2.52
    ⾊
    2.50
    愎
    2.50
    橚
    2.44
    
    2.41
    Activations Density 0.000%

    No Known Activations