© 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. 219342
    Prev
    Next
    INDEX
    Explanations

    birth, mom, kids, food

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

    Status, Accounting, IQ, URL, SEO

    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
     放
    0.48
     hoá
    0.47
     ձ
    0.45
     상품
    0.44
     香港
    0.44
    قى
    0.43
     enormes
    0.43
     作品
    0.42
    叢
    0.42
     产品
    0.42
    POSITIVE LOGITS
    dır
    0.54
     perto
    0.49
    हा
    0.48
    kas
    0.48
    ção
    0.47
    ¹
    0.47
     implemented
    0.47
    nvidia
    0.46
    encoding
    0.45
    implementation
    0.45
    Activations Density 0.000%

    No Known Activations