© 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. 222674
    Prev
    Next
    INDEX
    Explanations

    most closely

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

    listing for keywords

    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
    )،
    0.51
    これも
    0.51
     desayuno
    0.48
     começou
    0.47
     desarrollando
    0.47
     papá
    0.47
     религиоз
    0.46
    )=>{
    0.46
    面に
    0.46
    )==
    0.45
    POSITIVE LOGITS
    LUT
    0.45
    睑
    0.42
     оці
    0.41
    Committee
    0.41
     Committee
    0.40
    MA
    0.40
    ്ട
    0.39
    戏剧
    0.38
     {}
    0.38
     evidenced
    0.38
    Activations Density 0.002%

    No Known Activations