© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    starting sentences or phrases

    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
     их
    -0.84
    Archiv
    -0.82
     görüntüsü
    -0.78
    Batt
    -0.77
     Archiv
    -0.77
    YES
    -0.77
     lavable
    -0.76
    なんだろう
    -0.75
    ولد
    -0.73
     câble
    -0.73
    POSITIVE LOGITS
     according
    1.04
     to
    1.01
    ◙
    0.83
     Hình
    0.83
    ুর
    0.81
     оказалось
    0.81
    poshmark
    0.80
    ⮜
    0.79
    chainId
    0.79
    gaged
    0.78
    Activations Density 0.017%

    No Known Activations