© 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. 22-GEMMASCOPE-RES-131K
    7. 71132
    Prev
    Next
    INDEX
    Explanations

    door, then, behold

    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
     budete
    -1.13
     also
    -1.06
    ProgressHUD
    -0.97
    ServletContext
    -0.93
    ticus
    -0.92
     diesen
    -0.90
     sabemos
    -0.90
     permasalahan
    -0.90
     vertellen
    -0.90
     última
    -0.89
    POSITIVE LOGITS
    俱乐
    0.99
     taba
    0.96
    著者
    0.96
     chào
    0.94
    reve
    0.94
     viejas
    0.93
     culin
    0.93
     surprise
    0.92
     beheld
    0.92
    Behold
    0.91
    Activations Density 0.019%

    No Known Activations