© 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. 242661
    Prev
    Next
    INDEX
    Explanations

    bridal bouquet, APK file, blood pressure

    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
    드
    0.61
    眥
    0.54
    logne
    0.53
     زمین
    0.51
     कक्क
    0.51
     artériel
    0.50
    ຶ່ງ
    0.50
    ग
    0.48
    𒈗
    0.48
    மே
    0.47
    POSITIVE LOGITS
     realist
    0.54
     este
    0.51
    z
    0.50
     imag
    0.50
     geomét
    0.49
     oe
    0.48
     loader
    0.47
     acest
    0.47
    লোড
    0.47
     toda
    0.46
    Activations Density 0.001%

    No Known Activations