© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206239
    Prev
    Next
    INDEX
    Explanations

    national identity and practices

    np_acts-logits-general · gemini-2.5-flash-lite

    names, places, and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     плате
    0.55
    ⇢
    0.54
    🛖
    0.50
    🏕
    0.49
     होस्ट
    0.47
     शिला
    0.47
     प्रसारण
    0.47
    缆
    0.47
     प्रसार
    0.47
     concursos
    0.46
    POSITIVE LOGITS
     display
    0.40
     Nederlandse
    0.40
     border
    0.39
     typically
    0.39
     Poland
    0.39
     Adolph
    0.39
     applied
    0.38
     certain
    0.38
     Saudi
    0.38
     worn
    0.38
    Activations Density 0.000%

    No Known Activations