© 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. 200088
    Prev
    Next
    INDEX
    Explanations

    wedding day

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

    automating, formatting, or technical terms

    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
    羮
    0.49
    繇
    0.48
    лү
    0.47
    λη
    0.47
    пси
    0.46
     cland
    0.45
    気温
    0.45
    物业
    0.45
    стые
    0.44
     leftWheel
    0.44
    POSITIVE LOGITS
    </h2>
    0.65
    <0x0D>
    0.56
    F
    0.52
     }^{
    0.50
    Immediate
    0.50
    hausen
    0.49
    needs
    0.49
    u
    0.48
    parts
    0.48
    on
    0.48
    Activations Density 0.000%

    No Known Activations