© 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. 131361
    Prev
    Next
    INDEX
    Explanations

    unbeatable selection, wedding dresses

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

    artificial or separate entities

    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
     сиг
    0.55
    艐
    0.55
     adequ
    0.50
     당연
    0.50
     привы
    0.49
     solidify
    0.48
    Deve
    0.47
    کین
    0.47
     curto
    0.46
     adegu
    0.46
    POSITIVE LOGITS
    <0x0D>
    0.57
                    
    0.49
            
    0.46
     Latex
    0.45
    }"
    0.45
    webp
    0.44
    >
    0.44
    tic
    0.43
    xt
    0.42
    ård
    0.42
    Activations Density 0.001%

    No Known Activations