© 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. 38499
    Prev
    Next
    INDEX
    Explanations

    architectural features like porch

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

    walls, fortifications, defensive structures

    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
    yscrapers
    0.62
    各大
    0.53
    結晶
    0.52
     मंत्राल
    0.50
    Istanbul
    0.50
    <0x92>
    0.50
    解析
    0.49
    cities
    0.49
    仙台
    0.49
    🗼
    0.48
    POSITIVE LOGITS
     porch
    0.47
     pebb
    0.46
     Oven
    0.46
     bypass
    0.46
     volut
    0.45
     domu
    0.45
     casal
    0.45
     latéral
    0.44
     Newton
    0.44
     Door
    0.43
    Activations Density 0.042%

    No Known Activations