© 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. 22-GEMMASCOPE-RES-131K
    7. 128636
    Prev
    Next
    INDEX
    Explanations

    operator overloading comparison

    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_22/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
    continues
    -1.21
     luxus
    -1.01
     dieną
    -0.99
    ysing
    -0.96
    katkan
    -0.96
    detek
    -0.94
    瑗
    -0.94
    giày
    -0.93
     esos
    -0.93
    AfterViewInit
    -0.92
    POSITIVE LOGITS
     this
    0.92
    by
    0.88
    VILLE
    0.86
    this
    0.84
     peers
    0.82
     EXACT
    0.82
     Բ
    0.79
    ={
    0.79
    3
    0.76
    除了
    0.75
    Activations Density 0.002%

    No Known Activations