© 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. 11125
    Prev
    Next
    INDEX
    Explanations

    nothing wrong with

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

    normal, healthy, okay

    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
     важней
    0.44
    Lac
    0.42
    جل
    0.39
    руются
    0.38
     ৭৭
    0.38
    iąz
    0.38
     misery
    0.38
    漆
    0.38
    Tiempo
    0.38
    lac
    0.37
    POSITIVE LOGITS
     legitimate
    0.75
     нормально
    0.71
     harmless
    0.70
     괜찮
    0.69
     legitimately
    0.68
    合理
    0.65
    正常的
    0.64
     lawful
    0.64
    合法
    0.61
     legít
    0.60
    Activations Density 0.078%

    No Known Activations