© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1951
    Prev
    Next
    INDEX
    Explanations

    try...except blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    на
    2.22
    ন
    2.02
    т
    1.95
    ni
    1.93
    ди
    1.92
    स
    1.90
    ं
    1.90
    י
    1.90
    ist
    1.89
    te
    1.88
    POSITIVE LOGITS
    ありますが
    2.11
     financeiros
    2.09
    あります
    1.98
    ように
    1.96
     mínimos
    1.87
    しっかり
    1.84
    Когда
    1.82
     博文
    1.80
    إ
    1.79
     Portanto
    1.78
    Activations Density 0.171%

    No Known Activations