© 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. 32729
    Prev
    Next
    INDEX
    Explanations

    names and titles followed by comma

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

    names followed by descriptors

    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
     અલગ
    0.39
    Td
    0.38
    <unused1>
    0.37
    <unused13>
    0.37
     និង
    0.36
     나가
    0.35
     sowas
    0.35
     αλλά
    0.35
     intuition
    0.35
     पैकिंग
    0.35
    POSITIVE LOGITS
     selaku
    1.13
    ،
    1.00
    ，
    0.90
    ,
    0.87
    ซึ่ง
    0.78
    ၊
    0.77
     ،
    0.77
    *,
    0.75
     ,
    0.75
     iaitu
    0.74
    Activations Density 0.094%

    No Known Activations