© 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. 233388
    Prev
    Next
    INDEX
    Explanations

    various natural processes

    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
     результатом
    0.51
     아닌
    0.47
    uyoruz
    0.47
    𝔰
    0.46
    の結果
    0.46
    İlk
    0.46
     स्वीकार
    0.46
    ITIONAL
    0.46
     결국
    0.45
     사람은
    0.45
    POSITIVE LOGITS
     Northwest
    0.60
     June
    0.54
     August
    0.54
    <0xAF>
    0.53
     High
    0.53
     Aug
    0.50
     Oct
    0.50
     highly
    0.49
     Hong
    0.49
     Highly
    0.49
    Activations Density 0.004%

    No Known Activations