© 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. 98110
    Prev
    Next
    INDEX
    Explanations

    special order review systems severe

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

    logical flow, common in

    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
     Zealand
    0.55
     United
    0.49
     l
    0.48
     kilogram
    0.48
     Congress
    0.48
     células
    0.47
     Islamic
    0.47
     Iranian
    0.47
     Sikhs
    0.46
     University
    0.46
    POSITIVE LOGITS
    馔
    0.54
    订阅
    0.50
     напомина
    0.50
     चट
    0.50
    🗑
    0.47
    Expires
    0.47
     공유
    0.47
     напом
    0.47
     همیشه
    0.46
    ⺀
    0.46
    Activations Density 0.001%

    No Known Activations