© 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. 233501
    Prev
    Next
    INDEX
    Explanations

    Dangerous Goods and regulations

    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
    ಿಂತ
    0.43
    andte
    0.43
    してみてください
    0.42
    ാനി
    0.42
    ordine
    0.42
    缐
    0.41
    िति
    0.40
    ENTIAL
    0.40
     Cached
    0.40
    إذا
    0.40
    POSITIVE LOGITS
     הר
    0.55
     recruited
    0.51
    ได้รับ
    0.50
    ພ
    0.49
     tuyển
    0.49
     adoles
    0.47
     wybr
    0.47
     gerekli
    0.46
     lệ
    0.46
     atl
    0.46
    Activations Density 0.000%

    No Known Activations